© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119040
    Prev
    Next
    INDEX
    Explanations

    definition and declaration keywords

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

    variable names or identifiers in code that contain the letter 'i' (often as a prefix, suffix, or standalone character).

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

    This neuron fires on occurrences of the identifier “find” (e.g. calls to a find() method).

    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
     and
    -1.77
     or
    -1.64
     in
    -1.59
     godk
    -1.45
    artney
    -1.41
     часть
    -1.38
    ledad
    -1.36
     потому
    -1.27
     específicos
    -1.26
    ческие
    -1.24
    POSITIVE LOGITS
    mathrm
    1.63
     invita
    1.53
     подходя
    1.43
     obliga
    1.35
     some
    1.35
    を行い
    1.32
     competen
    1.30
     соответству
    1.29
     gainera
    1.29
     europea
    1.28
    Activations Density 0.005%

    No Known Activations