© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116879
    Prev
    Next
    INDEX
    Explanations

    granular appearance

    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_16_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
    ಸ್
    0.52
     கணி
    0.52
    
    0.50
    omegal
    0.49
     בג
    0.45
    thirty
    0.45
     capit
    0.45
     پرون
    0.45
    anée
    0.45
     घटनास्थल
    0.45
    POSITIVE LOGITS
    G
    0.47
     emocionante
    0.43
    Women
    0.42
     猫
    0.42
    M
    0.41
    ”
    0.41
    戏
    0.41
     देखभाल
    0.41
    Cats
    0.41
    猫
    0.41
    Activations Density 0.000%

    No Known Activations