© 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. 7931
    Prev
    Next
    INDEX
    Explanations

    to take or obtain

    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
    }$
    -2.38
    ו
    -2.19
     WITH
    -2.19
    鲼
    -2.16
     RSITY
    -2.13
    ;
    -2.11
    鹇
    -2.08
    ने
    -2.06
    mbers
    -2.05
     大人
    -2.05
    POSITIVE LOGITS
    それぞれの
    1.95
    ?
    1.94
    poň
    1.88
    肫
    1.84
    ༛
    1.82
    レビ
    1.77
    驺
    1.77
    はいけない
    1.68
     were
    1.67
    /**
    1.67
    Activations Density 0.000%

    No Known Activations