© 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. 9200
    Prev
    Next
    INDEX
    Explanations

    skills learning abilities

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

    structured learning examples

    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
     policewomen
    0.36
     bibliographic
    0.36
    鷸
    0.35
     instantiate
    0.34
     computational
    0.34
     authenticate
    0.33
    unnel
    0.33
    や
    0.33
     annotate
    0.32
     sanitize
    0.32
    POSITIVE LOGITS
     umiejęt
    0.39
     aprend
    0.39
     Skills
    0.38
     Lifestyle
    0.37
     başlang
    0.37
     Fähigkeiten
    0.37
    Learning
    0.37
     Skill
    0.36
    强势
    0.36
    兴奋
    0.36
    Activations Density 0.000%

    No Known Activations