© 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. 127924
    Prev
    Next
    INDEX
    Explanations

    singular experience

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

    celebrate mistakes

    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
    ۳
    0.61
    ۲
    0.52
     Архі
    0.51
    ۵
    0.51
    ۹
    0.49
    ۶
    0.49
    ۰
    0.49
    ۴
    0.49
    Когда
    0.48
    ೨
    0.48
    POSITIVE LOGITS
    o
    0.52
    Money
    0.48
    TypeName
    0.46
    ící
    0.44
    ickey
    0.44
     Money
    0.43
     fallacy
    0.43
    solution
    0.43
    uster
    0.42
    ptid
    0.42
    Activations Density 0.000%

    No Known Activations