© 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. 24-GEMMASCOPE-2-RES-262K
    7. 11728
    Prev
    Next
    INDEX
    Explanations

    code blocks and file operations

    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
    以及
    0.34
    、『
    0.34
    它
    0.33
    同样
    0.31
    新潟
    0.31
     valamint
    0.30
    依次
    0.30
     آنا
    0.30
    他に
    0.29
    ंडी
    0.29
    POSITIVE LOGITS
     hadn
    0.41
    cual
    0.41
     도
    0.39
    들이
    0.39
     Wouldn
    0.39
     फ़ोन
    0.38
     שלא
    0.38
     deterioro
    0.38
     самых
    0.37
     przer
    0.37
    Activations Density 0.038%

    No Known Activations