© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103878
    Prev
    Next
    INDEX
    Explanations

    Naruto or storage

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

    phrases, lists, and code

    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
    гка
    0.55
     concreto
    0.48
    ット
    0.48
     dios
    0.47
     gto
    0.46
    arbeitung
    0.46
     olds
    0.45
    钴
    0.45
     TEX
    0.44
     chatt
    0.44
    POSITIVE LOGITS
     Bine
    0.46
     R
    0.45
     Cyclic
    0.43
    BufOffset
    0.42
     I
    0.42
     Immer
    0.42
    bine
    0.42
     Hidden
    0.42
     Electric
    0.41
     hidden
    0.41
    Activations Density 0.000%

    No Known Activations