© 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. 7805
    Prev
    Next
    INDEX
    Explanations

    little girl

    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
    _
    0.36
    在
    0.33
    ),
    0.33
     unserer
    0.32
     शैक्षणिक
    0.32
     Warsz
    0.31
    {\
    0.31
     Phương
    0.31
     },
    0.31
     Gün
    0.31
    POSITIVE LOGITS
    ᧐
    0.35
     pavattati
    0.32
    ⅼ
    0.31
     maken
    0.30
    ߋ
    0.30
    ⲟ
    0.30
    ԁ
    0.29
     marketers
    0.29
     کنی
    0.29
     puedas
    0.28
    Activations Density 0.000%

    No Known Activations