© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41075
    Prev
    Next
    INDEX
    Explanations

    design, security, protocols, fields, Heat, disaster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     автомоби
    0.48
     обучения
    0.46
     %),
    0.44
     файл
    0.44
     noqa
    0.44
     обучение
    0.43
    ’),
    0.43
    TTS
    0.43
     tất
    0.43
     запах
    0.43
    POSITIVE LOGITS
    teres
    0.48
     tropical
    0.45
    trop
    0.45
     dining
    0.44
    tering
    0.42
    weis
    0.42
    터를
    0.42
    頓
    0.42
     woman
    0.41
     conservatives
    0.41
    Activations Density 0.010%

    No Known Activations