© 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. 80839
    Prev
    Next
    INDEX
    Explanations

    payment and description

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

    AI and programming contexts

    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
    优质
    0.46
    幼儿园
    0.45
    ણા
    0.44
     Derbyshire
    0.43
    ൃ
    0.43
    担
    0.43
    ahlt
    0.43
    ladung
    0.43
     Gericht
    0.42
     gratuitos
    0.42
    POSITIVE LOGITS
     meters
    0.56
     /*
    0.52
     również
    0.50
     irritable
    0.50
     chose
    0.49
     също
    0.47
     can
    0.46
     micelles
    0.46
     ousted
    0.46
     멤버
    0.46
    Activations Density 0.000%

    No Known Activations