© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21172
    Prev
    Next
    INDEX
    Explanations

    code block initiators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ك
    0.45
     무
    0.43
     ק
    0.42
     ג
    0.41
     الب
    0.39
     베
    0.38
     وال
    0.37
     ב
    0.37
     לה
    0.36
     ו
    0.36
    POSITIVE LOGITS
    vonne
    0.39
    યોગ
    0.39
     izinsuku
    0.36
    lexer
    0.36
     AlertDialog
    0.35
    থানি
    0.35
    ₁.
    0.34
    ˌ
    0.34
    ⛎
    0.34
    的其他
    0.34
    Activations Density 0.276%

    No Known Activations