© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    يم
    0.77
    ه
    0.77
    يبة
    0.77
    لس
    0.73
    ၀၀
    0.72
    ينة
    0.71
     في
    0.70
    িম
    0.69
    ИН
    0.68
    في
    0.67
    POSITIVE LOGITS
    t
    1.16
    f
    1.06
    m
    0.91
     that
    0.88
    w
    0.88
    3
    0.84
     de
    0.83
    v
    0.82
    1
    0.82
     has
    0.81
    Activations Density 0.001%

    No Known Activations