© 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. 127863
    Prev
    Next
    INDEX
    Explanations

    there is/are

    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
    ignment
    -1.92
    𐀀
    -1.92
     indican
    -1.92
    oused
    -1.91
    葙
    -1.91
    珖
    -1.89
     aident
    -1.88
    烔
    -1.88
    ܆
    -1.87
    鶲
    -1.87
    POSITIVE LOGITS
     \&
    2.56
    </b>
    2.14
     этого
    2.11
     also
    2.08
     now
    2.08
     and
    2.05
     of
    1.98
     такого
    1.97
     with
    1.91
     προϊόν
    1.89
    Activations Density 0.070%

    No Known Activations