© 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. 14373
    Prev
    Next
    INDEX
    Explanations

    mitigation

    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_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
    al
    -2.69
    I
    -2.53
    ⟢
    -2.31
    en
    -2.30
    人和
    -2.27
    猻
    -2.22
    Leírás
    -2.20
     we
    -2.17
     surpass
    -2.13
    इटम
    -2.13
    POSITIVE LOGITS
    潆
    2.92
    回来了
    2.61
    ᠁
    2.59
    屃
    2.55
    镲
    2.44
    耵
    2.31
     cadeiras
    2.30
    囯
    2.25
     parachoque
    2.25
     哪些
    2.25
    Activations Density 0.002%

    No Known Activations