© 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. 100637
    Prev
    Next
    INDEX
    Explanations

    upcoming films or age and proceedings

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

    examples or concepts

    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
    k
    0.55
    0
    0.54
    j
    0.54
     ۵
    0.52
    5
    0.52
    s
    0.51
    4
    0.50
    ۰
    0.50
    ﺪ
    0.48
    3
    0.48
    POSITIVE LOGITS
    感が
    0.50
    âni
    0.43
    饪
    0.43
    劻
    0.43
    敚
    0.41
    ErrorInfo
    0.40
     కల
    0.39
     runga
    0.39
     Redd
    0.38
    讹
    0.38
    Activations Density 0.000%

    No Known Activations