© 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. 173475
    Prev
    Next
    INDEX
    Explanations

    car interior

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

    avoid, just, Role, Jack, Con

    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
     режисс
    0.47
     Беларуси
    0.47
    드
    0.46
     Крим
    0.46
    zaam
    0.45
    зму
    0.44
    मा
    0.43
    agm
    0.43
    乘客
    0.43
     Кри
    0.42
    POSITIVE LOGITS
    ပဲ
    0.52
     belly
    0.49
     policía
    0.47
     basilaires
    0.46
    ಿದ್ದಾನೆ
    0.46
    }$-
    0.45
     userData
    0.45
     paramètres
    0.43
     woodwork
    0.43
    াবলীর
    0.43
    Activations Density 0.000%

    No Known Activations