© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2547
    Prev
    Next
    INDEX
    Explanations

    sedan SEL trim

    np_acts-logits-general · gemini-2.5-flash-lite

    python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    윌
    0.27
    ى
    0.25
    Campbell
    0.25
    ERICK
    0.25
    쑥
    0.24
    Webster
    0.24
    yzed
    0.24
     McCorm
    0.24
    dinner
    0.23
    قبل
    0.23
    POSITIVE LOGITS
    と
    0.26
     t
    0.26
    ";
    0.26
     image
    0.25
     slog
    0.25
     detected
    0.25
    与
    0.25
     literals
    0.24
     libc
    0.24
     be
    0.24
    Activations Density 0.613%

    No Known Activations