© 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. 102089
    Prev
    Next
    INDEX
    Explanations

    component testing and casino bonuses

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

    insurance, common, length, return

    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
    +
    0.54
    h
    0.50
    O
    0.47
     Spencer
    0.46
    I
    0.45
    и
    0.44
    wt
    0.43
    C
    0.41
    H
    0.41
    N
    0.40
    POSITIVE LOGITS
     دیگه
    0.47
    Institution
    0.46
    Cuánto
    0.45
    custList
    0.45
    Fragmentation
    0.45
    InputValue
    0.44
    েনের
    0.44
     Bakufu
    0.43
    ژگی
    0.43
     shouldUse
    0.42
    Activations Density 0.000%

    No Known Activations