© 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. 8725
    Prev
    Next
    INDEX
    Explanations

    AI, ML, and related fields

    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
    သော
    0.34
     '\''
    0.34
    extré
    0.34
    echolog
    0.34
     BigDecimal
    0.33
    ແລະ
    0.33
     depositors
    0.33
     '>'
    0.33
    ₁,
    0.33
    POSITIVE LOGITS
    Kya
    0.40
    ത്രി
    0.39
    קה
    0.38
     ਕ
    0.38
     keren
    0.37
     trgov
    0.37
    izie
    0.37
    STE
    0.37
    ヒ
    0.36
     L
    0.36
    Activations Density 0.257%

    No Known Activations