© 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-65K
    7. 50921
    Prev
    Next
    INDEX
    Explanations

    introduces section or descriptor

    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_65k_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
    至于
    0.37
    <0xC2>
    0.36
     unor
    0.36
     variegated
    0.33
    تالي
    0.33
    nost
    0.32
     tenue
    0.32
     allerlei
    0.32
    いろいろ
    0.32
     of
    0.32
    POSITIVE LOGITS
    这两个
    0.37
     هات
    0.36
    齁
    0.36
     இவ்வ
    0.36
     NORTH
    0.36
    ḓ
    0.36
    ೭
    0.35
     Acet
    0.35
    瓤
    0.35
     कार्याल
    0.35
    Activations Density 0.130%

    No Known Activations