© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93329
    Prev
    Next
    INDEX
    Explanations

    iconic roles and captivating beauty

    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
    ма
    0.54
    たる
    0.53
    ся
    0.52
    म
    0.50
     abandonar
    0.49
     свое
    0.49
    ட்ஸ்
    0.49
     теку
    0.48
    Ｓ
    0.48
     своем
    0.48
    POSITIVE LOGITS
     lighting
    0.52
     Bible
    0.50
     inflammatory
    0.50
     racing
    0.50
     Biblical
    0.50
     rare
    0.49
     cinematic
    0.49
     life
    0.48
     women
    0.48
     science
    0.48
    Activations Density 0.001%

    No Known Activations