© 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. 158550
    Prev
    Next
    INDEX
    Explanations

    United States

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

    Admin API, provides guidance

    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
    ].
    0.42
     calculators
    0.42
     calculator
    0.42
    anning
    0.41
    ó
    0.41
     readily
    0.41
     pecuniary
    0.40
     also
    0.39
     والذي
    0.39
     ó
    0.39
    POSITIVE LOGITS
    Framework
    0.63
    Bm
    0.55
     ጥላ
    0.54
    Бар
    0.52
    Transform
    0.49
    arag
    0.49
    Dp
    0.48
    Threshold
    0.48
    TITLE
    0.48
    Bk
    0.48
    Activations Density 0.000%

    No Known Activations