© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 21244
    Prev
    Next
    INDEX
    Explanations

    Witnesses, perception, initial brief

    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
     ماشینونه
    0.44
     জনগণের
    0.40
    欵
    0.39
     συγκεκρι
    0.39
    Virtualized
    0.38
     ممال
    0.37
     годах
    0.37
     роках
    0.37
     సమీ
    0.37
    墠
    0.37
    POSITIVE LOGITS
     week
    0.50
     Week
    0.49
    iyim
    0.45
     poetry
    0.45
     onda
    0.44
     alpha
    0.43
     selfie
    0.43
    2
    0.43
    8
    0.43
     short
    0.42
    Activations Density 0.004%

    No Known Activations