© 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. 222280
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    describing parts and properties

    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
    text
    0.61
    Aless
    0.54
    TEXT
    0.51
    nice
    0.50
    Цена
    0.50
    ᴰ
    0.50
    Anna
    0.49
    Congrats
    0.49
    Jenn
    0.48
    Од
    0.48
    POSITIVE LOGITS
     ć
    0.51
     儿
    0.47
     êtres
    0.47
     hjust
    0.47
     epis
    0.46
     ασ
    0.46
     seg
    0.45
     ì
    0.44
     عش
    0.44
     satisfe
    0.43
    Activations Density 0.000%

    No Known Activations