© 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. 180796
    Prev
    Next
    INDEX
    Explanations

    logical unit or concept

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

    status, game, killing, MA, cynicism

    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
     informações
    0.57
     하기
    0.50
     signifikan
    0.50
     কো
    0.48
     oxidative
    0.47
     oficio
    0.47
    장
    0.47
     exercer
    0.46
    정이
    0.46
     étn
    0.46
    POSITIVE LOGITS
    鍬
    0.54
    eer
    0.51
    راہ
    0.48
    ینڈ
    0.48
    ე
    0.46
     բ
    0.44
    ườ
    0.43
    خوان
    0.43
    այ
    0.43
    ಾರದ
    0.43
    Activations Density 0.000%

    No Known Activations