© 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. 50476
    Prev
    Next
    INDEX
    Explanations

    exclusive collection, challenge might

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

    mystery, noir, research, remix

    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
     第一
    0.54
    第一
    0.49
    ጶ
    0.47
     UpdateWindow
    0.46
    ırmaya
    0.46
    
    0.46
    只
    0.45
     geworden
    0.45
     ghetto
    0.44
     gera
    0.44
    POSITIVE LOGITS
    midi
    0.48
    o
    0.47
     berths
    0.44
    <eos>
    0.42
     latérales
    0.42
    står
    0.42
    idah
    0.41
    Medieval
    0.41
    u
    0.41
    Employment
    0.41
    Activations Density 0.000%

    No Known Activations