© 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. 128061
    Prev
    Next
    INDEX
    Explanations

    grammar rules and concepts

    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
     They
    -3.34
     unſ
    -2.78
    訁
    -2.70
    
    -2.67
    튿
    -2.63
     dreary
    -2.59
     ſever
    -2.45
    jaqueta
    -2.45
     nových
    -2.41
    𐐀
    -2.38
    POSITIVE LOGITS
    I
    2.69
    A
    2.19
    O
    2.17
    C
    2.14
     одежду
    2.11
    as
    2.06
    by
    2.05
    man
    2.05
    >
    1.98
     ""));
    1.97
    Activations Density 0.008%

    No Known Activations