© 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. 245641
    Prev
    Next
    INDEX
    Explanations

    definitions and system components

    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
     杯
    0.49
     ଶ
    0.48
    ulations
    0.48
     ఏర్ప
    0.47
    isation
    0.47
     軍
    0.47
     prosecute
    0.46
     ဒ
    0.46
    entown
    0.46
    isations
    0.46
    POSITIVE LOGITS
    ראה
    0.46
     Alia
    0.45
    Ná
    0.45
    ெற்ற
    0.45
    Naz
    0.45
    וט
    0.44
    Ұ
    0.44
    кугӀ
    0.44
    Į
    0.44
     Gret
    0.43
    Activations Density 0.000%

    No Known Activations