© 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. 13765
    Prev
    Next
    INDEX
    Explanations

    warning followed by colon

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

    punctuation followed by words

    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
     Section
    0.48
     named
    0.47
     Circular
    0.47
     Ref
    0.46
     её
    0.45
    appName
    0.44
    ’
    0.44
     Statue
    0.44
    ene
    0.44
     President
    0.44
    POSITIVE LOGITS
    大き
    0.50
    殺人
    0.49
    姦
    0.48
    馴染
    0.47
    ្នាក់
    0.47
    싶
    0.47
    ᕋ
    0.47
    gé
    0.47
    開設
    0.46
    DebugTest
    0.46
    Activations Density 0.000%

    No Known Activations