© 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. 30305
    Prev
    Next
    INDEX
    Explanations

    Spanish and French initial syllables

    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
    Географија
    -0.93
    管理员
    -0.90
     Squares
    -0.90
    administ
    -0.84
     DAVID
    -0.82
    ﷽
    -0.82
     作り方
    -0.81
    を持つ
    -0.81
    Obr
    -0.80
    Zubereitung
    -0.80
    POSITIVE LOGITS
     portata
    0.84
    際に
    0.76
     low
    0.75
     handful
    0.75
    總
    0.75
    labus
    0.73
     strong
    0.73
    ensuche
    0.73
     raggiung
    0.72
     continuation
    0.71
    Activations Density 0.007%

    No Known Activations