© 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. 179163
    Prev
    Next
    INDEX
    Explanations

    scan, garlic, invasion, vibrations, adventures

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

    rhythmic sweep of light/beam

    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
    (
    0.48
    two
    0.48
     رکھتا
    0.48
    $\
    0.47
    million
    0.44
    relay
    0.44
    environ
    0.44
    dict
    0.43
     ガラス
    0.43
    n
    0.43
    POSITIVE LOGITS
     olives
    0.50
     compressors
    0.50
    েব
    0.47
     uitz
    0.47
     abbey
    0.46
     الحالي
    0.46
     ممكن
    0.45
     gleichen
    0.44
    ضاف
    0.43
    椏
    0.43
    Activations Density 0.000%

    No Known Activations