© 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. 58328
    Prev
    Next
    INDEX
    Explanations

    Kota Tinggi, Skip Hire

    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
    éter
    -0.95
     joli
    -0.90
     แต
    -0.90
    otherwise
    -0.89
     Agrega
    -0.88
     haza
    -0.88
    けどね
    -0.88
     Begle
    -0.88
     mutta
    -0.85
     imprimé
    -0.85
    POSITIVE LOGITS
    elif
    1.83
     or
    1.73
     what
    1.53
     elseif
    1.27
     also
    1.27
     if
    1.17
     elif
    1.17
     oppure
    1.02
     andererseits
    1.00
     else
    0.97
    Activations Density 0.008%

    No Known Activations