© 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. 63922
    Prev
    Next
    INDEX
    Explanations

    credit cards

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

    utilizing flat surfaces

    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
    監視
    0.51
    WORLD
    0.47
    КО
    0.47
    フー
    0.47
    業界
    0.46
    אָ
    0.46
    弧
    0.46
     역사
    0.45
    COMPLETE
    0.45
    base
    0.45
    POSITIVE LOGITS
     miracles
    0.46
     vacancies
    0.46
    یین
    0.45
    ểm
    0.43
    璎
    0.42
     łyż
    0.42
     effectual
    0.42
    と思っています
    0.42
     vestiges
    0.42
     contributory
    0.42
    Activations Density 0.000%

    No Known Activations