© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21392
    Prev
    Next
    INDEX
    Explanations

    speaking or stating about team plans

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

    The neuron fires strongly around reporting-speech contexts—i.e. tokens at or just before the start of direct quotations or around speech-attribution verbs.

    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
     other
    -1.60
     from
    -1.44
    calciatore
    -1.20
     that
    -1.16
    ૨
    -1.13
     sizable
    -1.11
     substantial
    -1.09
    周泽
    -1.07
     Surprisingly
    -1.05
    ětí
    -1.03
    POSITIVE LOGITS
    不
    1.31
     utilisons
    1.27
     mesmos
    1.17
    equivalent
    1.15
     primeros
    1.14
     sempre
    1.11
     is
    1.10
     jego
    1.09
     totalidad
    1.09
     esfuerzan
    1.09
    Activations Density 0.048%

    No Known Activations