© 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. 20817
    Prev
    Next
    INDEX
    Explanations

    svg opening tag width

    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
    ।
    1.01
    ع
    0.93
    E
    0.92
     καθώς
    0.89
     όχι
    0.87
    al
    0.84
    I
    0.84
    ن
    0.83
    ;
    0.83
    ۸
    0.81
    POSITIVE LOGITS
    t
    1.21
     SVG
    1.20
    ta
    0.94
    the
    0.89
    ture
    0.82
     wegen
    0.78
    tive
    0.77
    ছে
    0.75
    AY
    0.73
    UAGE
    0.72
    Activations Density 0.003%

    No Known Activations