© 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. 491
    Prev
    Next
    INDEX
    Explanations

    lists, structure, categories

    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
    ᵢ
    0.62
     cattle
    0.58
    ⤷
    0.53
     expropri
    0.51
     utilizza
    0.50
     einer
    0.50
    Ꮐ
    0.49
    ➡️
    0.49
     pressing
    0.49
     capitalization
    0.48
    POSITIVE LOGITS
    <blockquote>
    0.63
    jazd
    0.61
    aną
    0.61
    ات
    0.61
    sight
    0.61
    <h2>
    0.60
    setOn
    0.60
    <h3>
    0.59
    hhhh
    0.58
    तंत्र
    0.56
    Activations Density 0.797%

    No Known Activations