© 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. 34-GEMMASCOPE-RES-131K
    7. 117756
    Prev
    Next
    INDEX
    Explanations

    citing

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

    This neuron fires on standalone numeric tokens (numbers and version-like digits).

    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
    ként
    -0.71
     Boswell
    -0.69
     Genie
    -0.68
    slavery
    -0.67
     Pute
    -0.65
     mule
    -0.65
    лови
    -0.64
     availed
    -0.64
    herren
    -0.64
    lexus
    -0.64
    POSITIVE LOGITS
    sobí
    0.78
     laid
    0.70
    laid
    0.66
    oteur
    0.65
    ondes
    0.63
     maman
    0.63
     acorde
    0.62
    Gw
    0.61
     Tactics
    0.61
    etal
    0.60
    Activations Density 0.053%

    No Known Activations