© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41334
    Prev
    Next
    INDEX
    Explanations

    maple syrup

    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_12_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
    ্নে
    0.85
    ofSeconds
    0.84
    ilibrium
    0.81
    ॓
    0.81
    eterminate
    0.80
     жизнью
    0.80
    нную
    0.79
     признаки
    0.79
    বাহিত
    0.78
     shabd
    0.76
    POSITIVE LOGITS
    ේශ
    0.70
    。
    0.69
    哋
    0.68
     internationaux
    0.68
     issus
    0.66
     स
    0.66
     trúc
    0.65
     خ
    0.64
    ।
    0.64
    驻
    0.63
    Activations Density 0.000%

    No Known Activations