© 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. 174905
    Prev
    Next
    INDEX
    Explanations

    fury road, inline skating

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

    keywords, topics, and specific entities

    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
    сная
    0.45
    枣
    0.43
    벤트
    0.42
     lignes
    0.41
    נית
    0.40
    فس
    0.40
    סטי
    0.40
    ємо
    0.40
    Verified
    0.40
    芋
    0.40
    POSITIVE LOGITS
    ill
    0.47
    acad
    0.46
    ）：
    0.46
    ூழ
    0.44
     drier
    0.44
    aluminium
    0.44
    inv
    0.43
    il
    0.43
    a
    0.42
    ahiran
    0.42
    Activations Density 0.001%

    No Known Activations