© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20377
    Prev
    Next
    INDEX
    Explanations

    knows, computer, statements, collection, technique, cards

    np_acts-logits-general · gemini-2.5-flash-lite

    analyze movements analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ті
    0.57
    Ха
    0.57
    юн
    0.55
    ת
    0.53
    ні
    0.52
    ン
    0.51
    מש
    0.51
    跇
    0.50
     після
    0.49
    после
    0.49
    POSITIVE LOGITS
     Biochem
    0.50
     FIGS
    0.46
     Computer
    0.46
     computerized
    0.46
     knows
    0.45
     Proteins
    0.44
     disamb
    0.44
     Fukuoka
    0.44
     publice
    0.44
     know
    0.43
    Activations Density 0.002%

    No Known Activations