© 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. 48509
    Prev
    Next
    INDEX
    Explanations

    booking and appointments

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

    arrests and historical invasions

    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
     curioso
    0.52
     slate
    0.50
    odet
    0.49
     antim
    0.47
    ;
    0.46
    alion
    0.46
    asen
    0.46
     nos
    0.45
    olome
    0.44
    ेर
    0.43
    POSITIVE LOGITS
    장을
    0.49
    口碑
    0.49
    ﾀ
    0.48
     Размер
    0.46
    Baş
    0.46
    élément
    0.44
    τεί
    0.44
    雙
    0.44
    Dul
    0.44
    ኗ
    0.43
    Activations Density 0.000%

    No Known Activations