© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19948
    Prev
    Next
    INDEX
    Explanations

    long enough

    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_16_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
    ση
    0.75
     Și
    0.73
    UserService
    0.71
     și
    0.70
    ⌔
    0.69
    ação
    0.68
     I
    0.66
    Forgot
    0.66
    amento
    0.63
    ación
    0.63
    POSITIVE LOGITS
    e
    1.02
    та
    0.89
    ta
    0.79
    la
    0.79
    ki
    0.77
    其他
    0.77
    ne
    0.76
    ين
    0.76
    ja
    0.75
    lo
    0.75
    Activations Density 0.002%

    No Known Activations