© 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. 40000
    Prev
    Next
    INDEX
    Explanations

    friendly

    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
    ↵
    -2.14
    </b>
    -1.63
     ряда
    -1.51
    </h2>
    -1.44
     также
    -1.36
     Fakten
    -1.32
    </em>
    -1.30
     a
    -1.30
    ocytes
    -1.30
    atsby
    -1.29
    POSITIVE LOGITS
    if
    1.84
    鶿
    1.56
    ₶
    1.45
     informaron
    1.43
     cade
    1.43
    鳢
    1.41
    vertida
    1.41
    zość
    1.38
    assuming
    1.38
    ながらも
    1.38
    Activations Density 0.015%

    No Known Activations