© 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. 69287
    Prev
    Next
    INDEX
    Explanations

    steps, natural, swimmers, assignee, button, level, career, sets, reaction, pants

    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
     and
    -4.19
    และ
    -1.93
     verschillende
    -1.63
     vijf
    -1.56
    tatu
    -1.48
     dezelfde
    -1.38
     oe
    -1.36
    や
    -1.36
     firs
    -1.36
     beoor
    -1.34
    POSITIVE LOGITS
     in
    2.44
     (
    1.59
     on
    1.55
     at
    1.48
     skjø
    1.43
     by
    1.41
     undeniably
    1.40
     supremely
    1.38
     ((
    1.36
     Having
    1.30
    Activations Density 0.113%

    No Known Activations