© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    `in no event`

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

    The neuron strongly responds to tokens that are sequences of digits or long runs of punctuation (e.g. numeric values, version numbers, separators), i.e. structured numeric or delimiter tokens.

    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
     cies
    -0.77
    ोल
    -0.76
    Distribuzione
    -0.71
     individu
    -0.69
    hWnd
    -0.68
     검
    -0.68
    quillas
    -0.66
     Hukum
    -0.66
     introdu
    -0.66
     tesettür
    -0.66
    POSITIVE LOGITS
    Epoch
    0.75
    uxedo
    0.73
    licité
    0.69
    Dsl
    0.69
    село
    0.68
     Storey
    0.66
    asgi
    0.66
     şə
    0.66
    iettivo
    0.65
    TextInput
    0.64
    Activations Density 0.045%

    No Known Activations