© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30705
    Prev
    Next
    INDEX
    Explanations

    fields and categories

    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
     in
    -1.90
     of
    -1.77
     for
    -1.53
     on
    -1.42
     by
    -1.31
     at
    -1.29
     with
    -1.24
     from
    -1.16
     With
    -1.15
     problemów
    -1.14
    POSITIVE LOGITS
     and
    1.46
    others
    1.28
     ITAL
    1.27
     uur
    1.25
     rester
    1.23
    ierzch
    1.23
     SEPTEMBER
    1.20
     kontin
    1.20
     ORIGINAL
    1.19
     OCTOBER
    1.18
    Activations Density 0.109%

    No Known Activations