© 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. 11300
    Prev
    Next
    INDEX
    Explanations

    warning about caution

    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
    it
    1.76
     clairement
    1.45
    𝙜
    1.38
    zeit
    1.38
     saper
    1.34
     compr
    1.33
    conditions
    1.33
     teu
    1.32
     nominate
    1.31
    Vendo
    1.31
    POSITIVE LOGITS
    ד
    1.83
    ﺘ
    1.78
    ре
    1.68
    ‌ی
    1.67
    ב
    1.67
    ﺸ
    1.63
    τητας
    1.61
    ﺴ
    1.57
    ﻤ
    1.54
    り
    1.53
    Activations Density 0.017%

    No Known Activations