© 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. 128092
    Prev
    Next
    INDEX
    Explanations

    exceptions and errors

    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
     
    -2.64
    蟥
    -2.34
     我
    -2.30
    鹋
    -2.19
    橚
    -2.17
    These
    -2.16
     هناك
    -2.09
     ofere
    -2.08
    ،
    -2.08
     他
    -2.06
    POSITIVE LOGITS
    棐
    2.39
    是怎么回事
    2.22
    ’，
    2.22
    旰
    2.09
    铂
    2.06
    ệc
    2.06
    好吗
    2.05
    猡
    2.03
    怎么回事
    2.00
    懨
    2.00
    Activations Density 0.001%

    No Known Activations