© 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. 16266
    Prev
    Next
    INDEX
    Explanations

    must implement

    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
    ే
    2.80
    ž
    2.70
     scare
    2.61
    ק
    2.50
    ంది
    2.49
    儡
    2.48
    ので
    2.44
    াজ
    2.44
     asal
    2.43
    oded
    2.41
    POSITIVE LOGITS
    s
    4.85
    ের
    4.06
    tive
    3.72
    t
    3.54
    ς
    3.43
    ا
    3.40
    tails
    3.39
    sman
    3.30
    iveness
    3.29
    ים
    3.29
    Activations Density 0.578%

    No Known Activations