© 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. 47823
    Prev
    Next
    INDEX
    Explanations

    England Athletics

    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
     Verlag
    -0.76
    公众号
    -0.75
     OVER
    -0.74
    ohjel
    -0.72
    Citations
    -0.71
     Eis
    -0.71
     fara
    -0.71
     duro
    -0.71
    茱
    -0.69
     esto
    -0.68
    POSITIVE LOGITS
     thờ
    0.77
    paru
    0.71
     indeed
    0.67
    ftant
    0.64
    VZ
    0.63
    روز
    0.63
    emmel
    0.63
    viron
    0.63
    rtf
    0.63
    utie
    0.62
    Activations Density 0.042%

    No Known Activations