© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43292
    Prev
    Next
    INDEX
    Explanations

    without variations

    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
    pecabe
    -2.67
    geſ
    -2.47
    стреча
    -2.28
     verkau
    -2.25
    ”،
    -2.23
     светло
    -2.23
     leaſt
    -2.20
    还是要
    -2.19
    ﹍﹍
    -2.19
     alrededores
    -2.17
    POSITIVE LOGITS
     —
    3.16
    л
    2.88
    𐑂
    2.67
    🫱
    2.39
     With
    2.19
     and
    2.14
    焢
    2.14
     Siehe
    2.09
    在我
    2.03
    ioare
    2.03
    Activations Density 0.002%

    No Known Activations