© 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. 46090
    Prev
    Next
    INDEX
    Explanations

    directed graphs

    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
     dieses
    0.70
    மர்
    0.65
     diese
    0.64
    خدام
    0.61
    .。
    0.61
    {
    0.61
    鼕
    0.60
     yardımcı
    0.60
    İY
    0.59
    ruktur
    0.59
    POSITIVE LOGITS
    u
    0.80
    an
    0.63
    in
    0.59
    g
    0.57
    a
    0.57
    the
    0.55
    v
    0.53
     $\
    0.49
    us
    0.48
    f
    0.46
    Activations Density 0.001%

    No Known Activations