© 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. 51803
    Prev
    Next
    INDEX
    Explanations

    missing crystal

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

    email text communication

    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
    ологі
    0.52
    ibilit
    0.51
    ilecek
    0.49
     디
    0.48
    lıkla
    0.48
    rolog
    0.45
    LER
    0.45
    uire
    0.45
    hetically
    0.45
     সহজেই
    0.45
    POSITIVE LOGITS
    張り
    0.47
    ない
    0.46
    やはり
    0.45
    滋
    0.45
     viên
    0.43
     Baja
    0.43
    咅
    0.43
    сці
    0.43
     Eurostile
    0.43
    文書
    0.42
    Activations Density 0.000%

    No Known Activations