© 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. 14984
    Prev
    Next
    INDEX
    Explanations

    over- prefix and phrases

    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
    en
    3.11
     overall
    2.80
    ്
    2.72
     subdirectory
    2.53
    ूट
    2.49
    一位
    2.47
    ৮
    2.46
    ussa
    2.45
     wafers
    2.45
    overall
    2.43
    POSITIVE LOGITS
    whelming
    3.00
    joyed
    2.95
    lapping
    2.92
    whel
    2.89
    zicht
    2.88
    leftrightarrow
    2.81
    tragung
    2.79
    ದಗ
    2.75
    🅔
    2.68
    SuspendLayout
    2.62
    Activations Density 0.219%

    No Known Activations