© 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. 181155
    Prev
    Next
    INDEX
    Explanations

    photographers. numbers. sore. floor. list

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

    consequences if compelled or determined

    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
    qx
    0.50
     ताल
    0.48
     券
    0.48
     viện
    0.46
    esley
    0.46
    eser
    0.45
     紙
    0.45
     бума
    0.44
     thao
    0.44
    wj
    0.44
    POSITIVE LOGITS
    ционно
    0.47
    ajú
    0.46
    櫚
    0.46
    циона
    0.45
    ாரு
    0.44
     intervent
    0.43
    ሑ
    0.43
    無需
    0.42
    诹
    0.42
     roles
    0.42
    Activations Density 0.001%

    No Known Activations