© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83918
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     noastre
    -0.92
    atshirt
    -0.86
     abundances
    -0.86
     einzigen
    -0.83
     Parteien
    -0.83
     then
    -0.82
     yalnızca
    -0.82
    iaire
    -0.80
     vostra
    -0.80
    จริง
    -0.79
    POSITIVE LOGITS
     if
    0.93
     unang
    0.93
     barri
    0.89
    とは
    0.84
    קה
    0.83
    Awful
    0.82
     siè
    0.81
    Theres
    0.81
     roul
    0.80
     paillettes
    0.80
    Activations Density 0.015%

    No Known Activations