© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91201
    Prev
    Next
    INDEX
    Explanations

    roles and classifications

    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
    derry
    -1.45
     EIGHT
    -1.36
     nothwendig
    -1.35
    Bibliografie
    -1.34
    Läs
    -1.34
    cked
    -1.33
     discuter
    -1.33
    /~
    -1.32
    itize
    -1.30
    earlier
    -1.30
    POSITIVE LOGITS
     of
    3.08
     in
    2.78
     from
    2.72
     with
    2.31
     for
    2.30
     at
    2.22
     on
    2.13
     all
    1.85
     after
    1.77
     by
    1.68
    Activations Density 0.130%

    No Known Activations