© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5927
    Prev
    Next
    INDEX
    Explanations

    French and Spanish language concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    0
    0.39
    ifferentiate
    0.38
    ův
    0.34
    <0xA2>
    0.33
    6
    0.32
    ֜
    0.32
     মুজিবের
    0.32
     frictionless
    0.31
    1
    0.31
    ֤
    0.31
    POSITIVE LOGITS
    as
    0.41
     Außen
    0.38
     இதனை
    0.37
     Although
    0.36
    ಗಳಲ್ಲಿ
    0.36
    <unused299>
    0.36
    ങ്ങളിലും
    0.35
    is
    0.34
     amplitude
    0.34
    ありました
    0.34
    Activations Density 0.085%

    No Known Activations