© 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. 22911
    Prev
    Next
    INDEX
    Explanations

    rounds, minutes, seconds, numbers

    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
    φορά
    0.38
    如果
    0.37
    iré
    0.37
    _{
    0.36
    ilidade
    0.36
     implode
    0.36
     investigate
    0.36
    又
    0.35
     estudar
    0.34
    列
    0.34
    POSITIVE LOGITS
     discs
    0.42
     Decorative
    0.41
     أنا
    0.41
     थीम
    0.41
     Terima
    0.41
     Obed
    0.40
     Stickers
    0.40
     Tab
    0.39
     stickers
    0.39
     Merchandise
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.