© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1472
    Prev
    Next
    INDEX
    Explanations

    p Suite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    y
    7.40
    ০
    7.09
    in
    7.04
    a
    6.70
    u
    6.61
    an
    6.42
    e
    6.41
    t
    6.39
    en
    6.22
    er
    6.12
    POSITIVE LOGITS
    了一个
    2.45
    Най
    2.17
    了一
    2.13
    infoHeader
    2.12
    Си
    1.99
    Й
    1.99
    सायिक
    1.95
    Золо
    1.95
    了一個
    1.94
    Когда
    1.93
    Activations Density 1.315%

    No Known Activations