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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1018
    Prev
    Next
    INDEX
    Explanations

    phrases connected by and

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

    The neuron fires on the main content words (capitalized nouns) in titles, headings, or bibliographic entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     навіть
    -1.14
     cualquier
    -1.07
     terão
    -1.00
     poderão
    -0.98
    必须要
    -0.98
     nawet
    -0.98
     quaisquer
    -0.97
    räck
    -0.97
     thậm
    -0.94
     любых
    -0.94
    POSITIVE LOGITS
     its
    2.69
     the
    2.28
     how
    1.90
     their
    1.65
     other
    1.61
     our
    1.52
     what
    1.45
     some
    1.27
     beyond
    1.25
     VIDEOTAPE
    1.23
    Activations Density 0.086%

    No Known Activations