© 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. 84349
    Prev
    Next
    INDEX
    Explanations

    specific word sequences

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

    project proposal

    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
    は
    0.55
    ＞
    0.52
    神奈川
    0.50
    ました
    0.49
     ব্যাপক
    0.49
    াল
    0.48
    ال
    0.47
    子の
    0.47
    貝
    0.47
    州市
    0.46
    POSITIVE LOGITS
    árs
    0.50
     ppw
    0.50
    PanelVisual
    0.48
     메소
    0.47
    kjav
    0.44
     lard
    0.43
    dry
    0.42
    మణ
    0.42
     dź
    0.42
     raff
    0.42
    Activations Density 0.000%

    No Known Activations