© 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. 49453
    Prev
    Next
    INDEX
    Explanations

    BYv

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

    GROUP BY clause

    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
     suivantes
    0.42
    ینګ
    0.41
    农
    0.40
    ㄈ
    0.40
     جنوبی
    0.40
     southwest
    0.39
    namely
    0.39
    ㄇ
    0.39
     श्री
    0.39
    ului
    0.38
    POSITIVE LOGITS
    各自
    0.55
     Vocês
    0.46
    äus
    0.45
     überall
    0.43
    ábado
    0.43
     semuanya
    0.43
    cere
    0.43
    彼此
    0.42
     كانوا
    0.42
     elkaar
    0.42
    Activations Density 0.000%

    No Known Activations