© 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. 116202
    Prev
    Next
    INDEX
    Explanations

    invitations and job offers

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

    algorithms, blocking, mechanical, advanced

    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
     Oj
    0.50
    inairement
    0.46
    铯
    0.46
     Lessee
    0.45
    zechoslovak
    0.45
    olok
    0.44
    ently
    0.44
     सेंट
    0.44
     gode
    0.44
    enders
    0.44
    POSITIVE LOGITS
    ற்
    0.55
     উদ্বেগ
    0.46
     помочь
    0.44
    被迫
    0.44
     muffled
    0.44
    わ
    0.44
     moistur
    0.43
    の中でも
    0.42
     disrupted
    0.42
    ު
    0.42
    Activations Density 0.000%

    No Known Activations