© 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. 59563
    Prev
    Next
    INDEX
    Explanations

    frequencies and measurements

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

    lists, enumeration, items

    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
     местности
    0.53
    िकुलम
    0.50
     ы
    0.48
     hatches
    0.47
     eleven
    0.47
    砶
    0.47
     satisfactor
    0.46
     быть
    0.46
     Narrative
    0.46
     Textured
    0.45
    POSITIVE LOGITS
    يتي
    0.52
    ừ
    0.49
    დნენ
    0.46
    etection
    0.46
    فا
    0.45
    يران
    0.44
     근
    0.44
    ياً
    0.43
    سي
    0.42
    scrire
    0.42
    Activations Density 0.000%

    No Known Activations