© 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. 183544
    Prev
    Next
    INDEX
    Explanations

    analysis, units, surgical, country

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

    delightful, short season

    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
     UP
    0.50
     contin
    0.47
    oric
    0.47
    럽
    0.46
    लाईन
    0.46
     prepaid
    0.46
     situa
    0.46
    Ồ
    0.45
    ルメ
    0.45
     DES
    0.44
    POSITIVE LOGITS
     годы
    0.50
    agnet
    0.49
     класу
    0.49
     искусства
    0.45
    ♕
    0.44
     воспомина
    0.43
     воде
    0.43
    瓣
    0.42
     angeles
    0.42
    ского
    0.41
    Activations Density 0.000%

    No Known Activations