© 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. 73056
    Prev
    Next
    INDEX
    Explanations

    HTML column classes

    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
    抨
    -1.35
     najwięks
    -1.34
     zufrieden
    -1.29
     the
    -1.29
     arī
    -1.28
    為に
    -1.26
     wspania
    -1.25
    になったら
    -1.24
     vollkommen
    -1.23
     ausgezeichnet
    -1.23
    POSITIVE LOGITS
     boxe
    1.46
    蒹
    1.42
    pherals
    1.41
    ϳ
    1.41
    礎
    1.41
     strategie
    1.40
    子は
    1.40
    tront
    1.38
    <0xA3>
    1.34
     marat
    1.33
    Activations Density 0.001%

    No Known Activations