© 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. 139301
    Prev
    Next
    INDEX
    Explanations

    correlation, impact, failed doping

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

    common feeling

    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
    हू
    0.49
    镐
    0.48
     intermediaries
    0.47
    Contracts
    0.46
     obstáculos
    0.46
     inhibitors
    0.46
     mediums
    0.46
     gladi
    0.46
     iconography
    0.45
    իս
    0.45
    POSITIVE LOGITS
    f
    0.59
     фев
    0.46
     ১৯৬
    0.45
    dose
    0.44
    opend
    0.44
     ਫ
    0.44
    getPath
    0.43
     современном
    0.43
     国産
    0.43
    了大
    0.43
    Activations Density 0.000%

    No Known Activations