© 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. 209449
    Prev
    Next
    INDEX
    Explanations

    used by

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

    customizable options and variations

    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
     iban
    0.54
     financi
    0.53
    あるいは
    0.49
     ຫຼື
    0.48
    ي
    0.47
     coû
    0.47
     asesinato
    0.47
    队长
    0.47
     продаж
    0.47
     cuid
    0.46
    POSITIVE LOGITS
    Paint
    0.49
    Outside
    0.46
     ヨ
    0.45
    います
    0.44
    Painted
    0.44
    RB
    0.43
     他
    0.43
     純正
    0.43
     ロー
    0.42
     調
    0.42
    Activations Density 0.005%

    No Known Activations