© 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. 132462
    Prev
    Next
    INDEX
    Explanations

    equally comfortable

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

    CVI, Tracing, Discovery, Components, Absorbing, Transmitting

    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
    但也
    0.49
    NaBr
    0.48
     Bennett
    0.47
    日本
    0.47
    ن
    0.45
     Dayan
    0.45
    星球
    0.44
     boarded
    0.44
    김
    0.44
     Daniels
    0.44
    POSITIVE LOGITS
     t
    0.54
     m
    0.53
     l
    0.52
     zes
    0.47
     lap
    0.47
     fit
    0.46
     程序
    0.46
     mol
    0.46
    ugel
    0.46
     З
    0.46
    Activations Density 0.000%

    No Known Activations