© 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. 68290
    Prev
    Next
    INDEX
    Explanations

    wildlife, growth, and literacy

    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
    ㎖
    -2.23
     &
    -2.06
     and
    -1.91
    鹛
    -1.88
    隳
    -1.73
     ketika
    -1.72
    –
    -1.66
     мост
    -1.63
    😫
    -1.63
    in
    -1.61
    POSITIVE LOGITS
    ).
    2.81
    蕻
    2.13
    袛
    2.05
    麁
    1.98
    曏
    1.95
    símbolo
    1.89
     Durchschnitt
    1.88
     Gehalt
    1.88
    馀
    1.86
    ”.
    1.85
    Activations Density 0.091%

    No Known Activations