© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104649
    Prev
    Next
    INDEX
    Explanations

    accessing object at index

    np_acts-logits-general · gemini-2.5-flash-lite

    the preposition "at" in programming contexts, particularly in method names and function parameters involving indices or positions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the literal token “at,” especially when it’s used in code or technical text to indicate a position or index (e.g. “object at index,” “didSelectItemAt,” numeric “at” occurrences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    se
    -1.52
    u
    -1.45
     mainly
    -1.44
    ers
    -1.42
    reonine
    -1.41
     also
    -1.35
    t
    -1.34
    神社
    -1.30
    Brainz
    -1.30
    now
    -1.29
    POSITIVE LOGITS
    Vind
    1.48
     cercanas
    1.48
     such
    1.40
     turísticos
    1.36
     pourrait
    1.33
     espirituales
    1.33
     interesantes
    1.32
     hermosos
    1.32
    Latino
    1.31
     októ
    1.30
    Activations Density 0.034%

    No Known Activations