© 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. 22-GEMMASCOPE-RES-131K
    7. 27671
    Prev
    Next
    INDEX
    Explanations

    Boolean checks

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

    The neuron fires on standalone numeric answer tokens—i.e. numbers representing computed results or scores rather than parts of equations or regular text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    分泌
    -0.94
     Там
    -0.90
     Евгений
    -0.85
    WAYS
    -0.82
     guantes
    -0.79
     AÑO
    -0.79
    kunta
    -0.79
     homicidio
    -0.78
    anmar
    -0.78
    Downloader
    -0.78
    POSITIVE LOGITS
    </tr>
    0.82
    <h4>
    0.80
    游戏亮点
    0.74
     velikost
    0.73
     finally
    0.71
     編
    0.71
    ></
    0.70
    ionales
    0.69
     calam
    0.68
     судь
    0.68
    Activations Density 0.078%

    No Known Activations