© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25820
    Prev
    Next
    INDEX
    Explanations

    names and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pasaba
    -1.15
     tillbaka
    -1.15
     psz
    -1.14
    🥡
    -1.14
    ！！
    -1.14
    ～
    -1.14
     febru
    -1.13
     ū
    -1.09
    --------------
    -1.09
     évêque
    -1.08
    POSITIVE LOGITS
     resultant
    1.10
    度に
    1.09
    に行った
    1.09
    并未
    1.09
     incomparable
    1.08
    Pág
    1.06
    つづく
    1.05
    度は
    1.04
    はずです
    1.04
    のでしょう
    1.03
    Activations Density 0.033%

    No Known Activations