© 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. 78103
    Prev
    Next
    INDEX
    Explanations

    financial figures and currencies

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    /
    -0.74
    JKLM
    -0.72
     maxx
    -0.71
     zaś
    -0.71
    etheless
    -0.71
    ादी
    -0.71
    bored
    -0.70
     Raid
    -0.69
    {//
    -0.69
    Tyl
    -0.69
    POSITIVE LOGITS
     İyi
    0.90
    選挙
    0.85
     spedizione
    0.82
     Tüm
    0.72
    Kim
    0.72
    SING
    0.70
    你先
    0.70
     Při
    0.69
    説明
    0.69
    HK
    0.69
    Activations Density 0.006%

    No Known Activations