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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9298
    Prev
    Next
    INDEX
    Explanations

    language snippets

    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
    ы
    1.68
    *}$
    1.66
    allowed
    1.65
    𝗪
    1.64
     ahí
    1.59
    latitude
    1.57
    Edges
    1.53
    如有
    1.53
    য়ে
    1.52
    Repositories
    1.51
    POSITIVE LOGITS
    но
    1.92
    ный
    1.79
    𝙩
    1.77
    𝙪
    1.76
    𝙧
    1.75
    ך
    1.65
    িক
    1.63
    нен
    1.61
    ierter
    1.60
    ierten
    1.60
    Activations Density 0.000%

    No Known Activations