© 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. 102221
    Prev
    Next
    INDEX
    Explanations

    actions and, decision can, certainly are

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

    power and practices

    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
     dearly
    0.50
     höchste
    0.48
    мии
    0.47
    рист
    0.46
     formatos
    0.46
    plein
    0.46
    🍮
    0.45
    dete
    0.45
    fält
    0.44
    大街
    0.43
    POSITIVE LOGITS
     case
    0.49
     rupee
    0.45
     dupatta
    0.44
     screenshots
    0.44
     screenshot
    0.43
     கட்டிட
    0.43
     jean
    0.43
     tattha
    0.42
    蠔
    0.42
     ತೆಗೆದುಕೊಳ್ಳ
    0.42
    Activations Density 0.000%

    No Known Activations