© 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. 161293
    Prev
    Next
    INDEX
    Explanations

    articles followed by descriptors

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

    your voice

    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
     શિક્ષણ
    0.56
    িং
    0.54
    経営
    0.53
    ен
    0.52
     ото
    0.48
    وت
    0.48
    ည့်
    0.46
    舩
    0.44
    тың
    0.44
    ରେ
    0.43
    POSITIVE LOGITS
     Arno
    0.47
    Bou
    0.44
    papa
    0.44
    heart
    0.43
    Replacement
    0.43
     junta
    0.43
     staffs
    0.43
     unfilled
    0.43
    Grat
    0.42
     এগ
    0.41
    Activations Density 0.000%

    No Known Activations