© 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. 119366
    Prev
    Next
    INDEX
    Explanations

    in, from, by, for, to, with

    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
    κέ
    -1.02
     estrada
    -0.97
    Versch
    -0.96
     direkt
    -0.96
     éta
    -0.95
     allé
    -0.92
     olması
    -0.91
     hés
    -0.91
    tuig
    -0.91
    versch
    -0.89
    POSITIVE LOGITS
     with
    2.08
     from
    1.69
     by
    1.48
     in
    1.46
     at
    1.45
     using
    1.31
     AND
    1.28
     against
    1.27
     into
    1.27
     as
    1.24
    Activations Density 0.165%

    No Known Activations