© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128078
    Prev
    Next
    INDEX
    Explanations

    wreaks havoc, enzyme

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

    non-English characters and programming language syntax.

    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
    .
    -3.55
    ꠥ
    -2.48
    癥
    -2.45
    ஂ
    -2.45
    柃
    -2.42
    𝜖
    -2.36
    赁
    -2.33
    ?"
    -2.31
    魴
    -2.31
    llten
    -2.27
    POSITIVE LOGITS
     they
    2.63
    >
    2.61
    ?
    2.47
    蹰
    2.38
     chanteuse
    2.31
    ❊
    2.19
     anfitrión
    2.17
     وكذلك
    2.16
     بالإضافة
    2.13
     beberapa
    2.11
    Activations Density 0.001%

    No Known Activations