© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10730
    Prev
    Next
    INDEX
    Explanations

    check your answer

    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
    ever
    1.32
    theless
    1.30
     muttered
    1.23
    Handler
    1.17
    에
    1.17
     emphasis
    1.16
    и
    1.15
     hjust
    1.15
    ї
    1.12
     boundary
    1.12
    POSITIVE LOGITS
     березня
    1.44
    $;
    1.27
     opér
    1.26
     davran
    1.20
     cinqui
    1.19
     espect
    1.19
    hg
    1.18
     बाजारों
    1.17
    𝚔
    1.17
     червня
    1.17
    Activations Density 0.001%

    No Known Activations