© 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. 127662
    Prev
    Next
    INDEX
    Explanations

    salt and pinch

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

    This neuron fires on references to pepper (and closely related spice terms).

    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
    Some
    -1.77
    For
    -1.72
    The
    -1.58
     This
    -1.52
    That
    -1.51
    These
    -1.45
    Because
    -1.45
     With
    -1.41
    Most
    -1.39
    An
    -1.37
    POSITIVE LOGITS
     Aún
    1.40
    colazione
    1.37
    釓
    1.35
    POUR
    1.32
    xaml
    1.32
    ⠖
    1.31
     Cualquier
    1.30
    ordnen
    1.30
     Luego
    1.29
     psycholog
    1.29
    Activations Density 0.008%

    No Known Activations