© 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. 81406
    Prev
    Next
    INDEX
    Explanations

    plain greek yogurt

    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
    マーク
    0.44
     Judge
    0.44
     വീഡിയോ
    0.41
    ্যালেঞ্জ
    0.40
    锟
    0.40
    nahmen
    0.40
    Ｅ
    0.40
     Cron
    0.40
     veremos
    0.40
    Caprio
    0.39
    POSITIVE LOGITS
     apparence
    0.52
     تھا۔
    0.51
    Salt
    0.50
     veya
    0.50
    或
    0.50
    ely
    0.49
     atmosfera
    0.49
     organismes
    0.48
    chosen
    0.47
     pâle
    0.46
    Activations Density 0.003%

    No Known Activations