© 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. 130941
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

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

    explaining analogies and consequences

    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
    的大
    0.52
    ইয়
    0.49
    哈
    0.47
     Mell
    0.45
     sparsebundle
    0.45
     pickups
    0.44
     intolerance
    0.43
    ⁰
    0.43
     applying
    0.43
    汉
    0.43
    POSITIVE LOGITS
    TrackAngle
    0.55
    UpdatedAt
    0.49
     イベント
    0.48
    WithName
    0.48
     士
    0.48
     خير
    0.47
     പക്ഷേ
    0.46
    Wit
    0.46
    Estab
    0.46
     עס
    0.45
    Activations Density 0.002%

    No Known Activations