© 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. 59835
    Prev
    Next
    INDEX
    Explanations

    attempted to

    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
    ে
    -2.20
    可以
    -2.16
    体を
    -2.14
    \
    -2.13
    In
    -2.03
     ساعة
    -2.03
     averse
    -2.00
    !!!!!!
    -2.00
    It
    -1.98
    いだ
    -1.96
    POSITIVE LOGITS
    趼
    2.61
    </em>
    2.39
    雠
    2.33
    珎
    2.28
     男士
    2.28
    ↵
    2.25
    髡
    2.25
    ኾ
    2.23
    ஂ
    2.22
    钲
    2.22
    Activations Density 0.007%

    No Known Activations