© 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. 22-GEMMASCOPE-RES-131K
    7. 128597
    Prev
    Next
    INDEX
    Explanations

    programming keywords: import, static, class

    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_22/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
     with
    -1.05
     to
    -1.02
     without
    -0.98
     Histórico
    -0.96
     in
    -0.93
    tesy
    -0.91
     by
    -0.91
    ريح
    -0.90
    gym
    -0.89
     that
    -0.87
    POSITIVE LOGITS
    Appellee
    0.96
     sekä
    0.94
    retmen
    0.87
    還有
    0.84
     Hautes
    0.83
     ועוד
    0.82
    liques
    0.81
     caminar
    0.81
    Appellants
    0.78
    还有
    0.77
    Activations Density 0.001%

    No Known Activations