© 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. 30935
    Prev
    Next
    INDEX
    Explanations

    thermal expansion

    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
    Y
    0.50
    OR
    0.49
     rightfully
    0.47
    ட்கள்
    0.46
    ட்க
    0.45
    ఊ
    0.45
    ید
    0.44
    Katherine
    0.44
     cultured
    0.43
    িকো
    0.43
    POSITIVE LOGITS
     သည်
    0.47
     千
    0.44
     這個
    0.43
    })-\
    0.42
     bucks
    0.42
     कवाय
    0.42
     عمليات
    0.42
     カル
    0.41
     ジャン
    0.41
     정
    0.41
    Activations Density 0.002%

    No Known Activations