© 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. 8463
    Prev
    Next
    INDEX
    Explanations

    primary key constraints on joins

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

    database constraints and keys

    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
     cultivés
    0.49
    💦
    0.48
    去年
    0.47
    граф
    0.47
     échange
    0.46
    ম্ভীর
    0.45
    鮭
    0.45
    ্রাজ
    0.44
     стрелецкой
    0.43
    もあった
    0.43
    POSITIVE LOGITS
    ↵
    0.61
    ing
    0.54
    CONSTRAINT
    0.54
     Advisor
    0.51
     constraint
    0.50
     CONSTRAINT
    0.49
    Constraint
    0.49
     on
    0.48
     ON
    0.47
     Constraint
    0.47
    Activations Density 0.000%

    No Known Activations