© 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. 131633
    Prev
    Next
    INDEX
    Explanations

    daily activities or dates

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

    increasing 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
    ית
    0.51
     いた
    0.49
    ため
    0.47
     घा
    0.46
     オフィス
    0.45
    ቕ
    0.44
     фильма
    0.44
     berguna
    0.44
    ァ
    0.43
    transfected
    0.43
    POSITIVE LOGITS
     ebenso
    0.46
     Everything
    0.39
    倾向
    0.38
     expertly
    0.38
     burgeoning
    0.38
     simmering
    0.38
     frisch
    0.37
    也不会
    0.37
    វ
    0.37
     Galloway
    0.36
    Activations Density 0.002%

    No Known Activations