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. 7517
    Prev
    Next
    INDEX
    Explanations

    construction and military

    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
    üh
    1.46
    襲
    1.36
    ıyla
    1.35
    TextMessage
    1.31
     таки
    1.30
     amel
    1.27
     prefecture
    1.26
    ël
    1.25
    ுக்
    1.25
    ليز
    1.24
    POSITIVE LOGITS
    naires
    1.43
    ই
    1.38
    tract
    1.32
    telling
    1.31
    rations
    1.31
    ead
    1.31
    িক
    1.30
    naire
    1.30
    ક
    1.30
    ted
    1.28
    Activations Density 0.000%

    No Known Activations