© 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. 10-GEMMASCOPE-RES-131K
    7. 9958
    Prev
    Next
    INDEX
    Explanations

    medical, financial, or educational reporting

    np_acts-logits-general · gemini-2.5-flash-lite

    colons that precede lists or bullet points.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -2.28
     we
    -1.85
     by
    -1.55
     and
    -1.48
     where
    -1.44
     to
    -1.38
     since
    -1.38
     as
    -1.30
    alitions
    -1.24
     From
    -1.23
    POSITIVE LOGITS
    珢
    1.56
    etcode
    1.47
    まず
    1.45
    
    1.41
    EqualsAnd
    1.40
    formatics
    1.39
    ogh
    1.38
     mentiras
    1.38
    titial
    1.36
    ：「
    1.35
    Activations Density 0.034%

    No Known Activations