© 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. 7589
    Prev
    Next
    INDEX
    Explanations

    comes to, fashion, you an

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

    requesting to produce a

    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
    characteristic
    0.34
    __.
    0.31
     காரண
    0.31
     TextAlign
    0.31
     характер
    0.31
    mathscr
    0.31
    HORIZONTAL
    0.30
    DEFINITION
    0.30
    㞒
    0.30
     formar
    0.30
    POSITIVE LOGITS
    様専用
    0.39
     overclock
    0.36
     skincare
    0.36
     veggies
    0.36
     ukulele
    0.36
     weddings
    0.36
     MotoGP
    0.36
     aftermarket
    0.35
     playthrough
    0.35
     WWE
    0.35
    Activations Density 1.878%

    No Known Activations