© 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. 124088
    Prev
    Next
    INDEX
    Explanations

    calibration

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

    representation of reality

    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
    u
    0.47
    adó
    0.47
    telegram
    0.46
     Cortés
    0.46
    undert
    0.44
    rsp
    0.44
    uot
    0.43
    interpret
    0.43
     ভাষায়
    0.43
    team
    0.42
    POSITIVE LOGITS
    ！！
    0.47
     calibrations
    0.46
    額
    0.45
    ຫລ
    0.45
     calibration
    0.45
    クリーム
    0.44
     modernisation
    0.44
     Calibration
    0.44
     foreclosure
    0.43
    理想
    0.43
    Activations Density 0.006%

    No Known Activations