© 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. 30965
    Prev
    Next
    INDEX
    Explanations

    annual/monthly/annualized updates or events

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

    concept of

    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
    ający
    0.50
     boundedness
    0.49
    jedno
    0.49
     okvir
    0.47
     விதி
    0.47
    ஜ
    0.47
     dostęp
    0.46
     programu
    0.46
     związane
    0.46
     डिलिवरी
    0.45
    POSITIVE LOGITS
    有
    0.46
    救
    0.42
    冗
    0.42
    粗
    0.41
    ，
    0.41
    追
    0.40
    刺激
    0.39
     moh
    0.39
     ra
    0.38
    LK
    0.38
    Activations Density 0.000%

    No Known Activations