© 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. 73582
    Prev
    Next
    INDEX
    Explanations

    ArrayList in code

    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
     시리즈
    0.43
     davran
    0.42
    运行
    0.41
    thane
    0.40
    ،
    0.40
    
    0.40
    💃
    0.40
     reales
    0.39
    蚊
    0.39
    具有
    0.39
    POSITIVE LOGITS
    iv
    0.62
    in
    0.54
    ov
    0.53
    จะไม่
    0.52
    t
    0.51
    ut
    0.51
    ip
    0.50
    出來
    0.49
    el
    0.49
    ivet
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.