© 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. 231303
    Prev
    Next
    INDEX
    Explanations

    standard or jewelry

    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
    ન
    0.57
    નિ
    0.54
     magnific
    0.48
     Incredible
    0.48
    电信
    0.48
     flights
    0.47
    export
    0.47
     incredible
    0.47
    न
    0.46
    नं
    0.46
    POSITIVE LOGITS
    URNIZOR
    0.49
    utlich
    0.49
     ll
    0.46
     dall
    0.46
    arlar
    0.45
    abah
    0.43
    äle
    0.43
     나올
    0.43
    QTTR
    0.42
     даст
    0.42
    Activations Density 0.000%

    No Known Activations