© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127790
    Prev
    Next
    INDEX
    Explanations

    breadth and wideness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shells
    0.63
    p
    0.57
     as
    0.56
    roll
    0.54
     on
    0.54
    r
    0.54
    ্লেখ
    0.53
    sar
    0.53
    sol
    0.52
    sz
    0.52
    POSITIVE LOGITS
    広い
    0.87
     broad
    0.84
     widened
    0.83
    넓
    0.82
    (
    0.80
     wide
    0.80
     broadened
    0.78
     widest
    0.77
     narrowed
    0.76
    広
    0.75
    Activations Density 0.072%

    No Known Activations