© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    quantities or lists

    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
    ка
    0.46
     in
    0.44
     an
    0.40
     be
    0.38
    }{
    0.37
     ɔ
    0.37
    ão
    0.36
     to
    0.36
    ;
    0.36
    ;|
    0.35
    POSITIVE LOGITS
    ان
    0.39
    os
    0.36
    い
    0.36
    ある
    0.35
    า
    0.33
     puluh
    0.31
     It
    0.31
    いっぱい
    0.30
    نا
    0.30
     However
    0.29
    Activations Density 0.900%

    No Known Activations