© 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. 115305
    Prev
    Next
    INDEX
    Explanations

    liability, God, payments, stars

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

    AI that weaves or shuts

    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
     キッチン
    0.49
    s
    0.47
    érable
    0.46
     Microbiology
    0.46
    a
    0.46
     ይታ
    0.45
    ния
    0.45
     процессов
    0.45
    ｓ
    0.45
     chú
    0.44
    POSITIVE LOGITS
    ქმ
    0.49
     appropriateness
    0.46
    駕駛
    0.46
     lije
    0.44
     društ
    0.44
     ആരാ
    0.44
     konzerv
    0.43
     ulic
    0.43
    Tamil
    0.43
    новништво
    0.42
    Activations Density 0.000%

    No Known Activations