© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75168
    Prev
    Next
    INDEX
    Explanations

    clear: both;

    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
     to
    -2.05
     для
    -1.17
     gebeten
    -1.16
     answers
    -1.07
     zimowe
    -1.04
     тысячи
    -1.04
    \\
    -1.04
    ↵↵
    -1.03
    <em>
    -1.02
     können
    -1.02
    POSITIVE LOGITS
     zey
    1.39
     biber
    1.29
     allan
    1.28
     prohi
    1.22
     monter
    1.16
     roca
    1.15
     communis
    1.15
    ậc
    1.13
     fich
    1.12
     puissance
    1.12
    Activations Density 0.003%

    No Known Activations