© 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. 228732
    Prev
    Next
    INDEX
    Explanations

    short periods

    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
     divine
    0.52
    товые
    0.45
     I
    0.45
     cantilever
    0.45
    ㅈ
    0.45
     Gah
    0.44
     Pember
    0.44
     heavenly
    0.43
     eloquence
    0.43
    จักร
    0.42
    POSITIVE LOGITS
     mejora
    0.54
     enfermedad
    0.50
     accidente
    0.50
    綠
    0.48
     škola
    0.47
    會
    0.47
     बना
    0.46
    班
    0.46
     améli
    0.46
    ői
    0.46
    Activations Density 0.000%

    No Known Activations