© 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. 22-GEMMASCOPE-RES-131K
    7. 11214
    Prev
    Next
    INDEX
    Explanations

    roles or titles following common words

    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_22/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
     lamentable
    -1.20
     pernic
    -1.16
     indispens
    -1.13
    imee
    -1.13
     preponder
    -1.09
    ύ
    -1.09
     intrigu
    -1.08
     devast
    -1.08
     suspic
    -1.06
     verschillende
    -1.06
    POSITIVE LOGITS
     who
    1.89
     in
    1.43
     also
    1.29
     of
    1.27
     before
    1.25
     an
    1.23
     at
    1.22
     during
    1.22
     then
    1.22
     on
    1.21
    Activations Density 0.038%

    No Known Activations