© 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. 187944
    Prev
    Next
    INDEX
    Explanations

    names and specific roles

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

    modelanalyze, descriptive, reduce

    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
    ية
    0.49
    ма
    0.48
    屠
    0.46
    le
    0.45
    >
    0.45
    毆
    0.44
    тан
    0.44
     želite
    0.44
    о
    0.44
     voulez
    0.44
    POSITIVE LOGITS
     부정
    0.47
     Ricky
    0.46
     renormal
    0.46
     afectadas
    0.46
     Cindy
    0.45
     حالی
    0.45
     Avoiding
    0.45
     hallmarks
    0.44
     Belinda
    0.44
     Lasso
    0.44
    Activations Density 0.000%

    No Known Activations