Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7390
    Prev
    Next
    INDEX
    Explanations

    current state or readiness

    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_9_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
    ‍♂️
    2.78
    𝗣
    2.48
    𝘂
    2.48
    𝗡
    2.39
    verständlich
    2.35
    𝗺
    2.23
    likle
    2.15
    pane
    2.15
    يكية
    2.09
    ء
    2.08
    POSITIVE LOGITS
    د
    3.01
    ب
    2.75
    л
    2.72
    ेक्षित
    2.70
    ia
    2.64
    на
    2.61
    rzed
    2.55
    getStatusCode
    2.39
    quele
    2.37
    welling
    2.29
    Activations Density 0.301%

    No Known Activations