© 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. 44628
    Prev
    Next
    INDEX
    Explanations

    code comments and directives

    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
     матч
    -1.54
     cilind
    -1.52
     principi
    -1.48
    )։
    -1.46
    altes
    -1.45
    forKey
    -1.41
     semua
    -1.40
     mientras
    -1.39
     psicologia
    -1.39
    ramid
    -1.37
    POSITIVE LOGITS
    也非常
    1.69
    utilisons
    1.58
    来て
    1.55
     basteln
    1.53
    очень
    1.50
    是非常
    1.49
    注意事项
    1.48
     głównie
    1.44
    蒾
    1.41
    TryDecode
    1.39
    Activations Density 0.010%

    No Known Activations