© 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. 65945
    Prev
    Next
    INDEX
    Explanations

    jurors are, imagine there, watch is

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

    Fastest speed

    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
    www
    0.43
     /.
    0.43
     language
    0.42
     Royaume
    0.42
     chère
    0.42
     diocese
    0.41
     ती
    0.41
     Estas
    0.40
     &
    0.40
     Cher
    0.40
    POSITIVE LOGITS
    ೇಯ
    0.51
     bolas
    0.51
    amphetamine
    0.48
    occasion
    0.47
    ጀመሪያ
    0.46
    ombres
    0.45
    וס
    0.44
    aterdag
    0.44
    CUIT
    0.44
    inputId
    0.44
    Activations Density 0.001%

    No Known Activations