© 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. 60026
    Prev
    Next
    INDEX
    Explanations

    proper noun nouns

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

    avoiding regret

    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
    inträ
    0.55
    kn
    0.51
    ið
    0.47
    铮
    0.46
    덥
    0.46
     stif
    0.45
    gatt
    0.45
     padres
    0.44
    ẩm
    0.44
    ў
    0.44
    POSITIVE LOGITS
     retainer
    0.50
     traduce
    0.49
     aryl
    0.47
     indexing
    0.47
     sublicense
    0.46
    េរ
    0.46
    လုံး
    0.46
     propriet
    0.46
     indemn
    0.46
     retain
    0.45
    Activations Density 0.001%

    No Known Activations