© 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. 33961
    Prev
    Next
    INDEX
    Explanations

    starting punctuation

    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
     LOCATION
    -0.79
    чется
    -0.76
     consumidor
    -0.75
     OFFERS
    -0.73
    容
    -0.72
     meditate
    -0.71
     demi
    -0.71
     federal
    -0.71
    cui
    -0.71
    bbbb
    -0.69
    POSITIVE LOGITS
     cerimonia
    0.87
     soprav
    0.87
     borsa
    0.85
    ră
    0.85
     voulais
    0.85
    Chất
    0.82
    BELL
    0.81
    ϝ
    0.81
     predecess
    0.80
    ÁL
    0.78
    Activations Density 0.074%

    No Known Activations