© 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. 41916
    Prev
    Next
    INDEX
    Explanations

    capture filters, libraries, or cards

    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
     as
    1.41
    та
    1.36
    т
    1.27
    א
    1.23
    к
    1.21
    ק
    1.12
    ت
    1.11
    ０
    1.11
     ഒരു
    1.06
    г
    1.05
    POSITIVE LOGITS
    ne
    1.69
    w
    1.36
    ur
    1.34
    m
    1.32
    5
    1.27
    9
    1.27
    ar
    1.26
    7
    1.26
    in
    1.25
    am
    1.25
    Activations Density 0.007%

    No Known Activations