© 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. 73193
    Prev
    Next
    INDEX
    Explanations

    local curiosities

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

    relationship, cumulative, conflict

    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
    괴
    0.50
     Pistol
    0.46
     緊急
    0.46
    kotlin
    0.46
     Goblin
    0.46
     Named
    0.45
    ㊙
    0.45
    祕
    0.45
     સફેદ
    0.44
     شهید
    0.44
    POSITIVE LOGITS
    因素
    0.47
     ಸ್ಥ
    0.47
    0.45
     vaid
    0.44
     اثر
    0.43
    テイン
    0.43
     ra
    0.42
    ｢
    0.42
    اظ
    0.41
    cans
    0.41
    Activations Density 0.000%

    No Known Activations