© 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. 10-GEMMASCOPE-RES-131K
    7. 70512
    Prev
    Next
    INDEX
    Explanations

    Markov chains, animator, Archiv

    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_10/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
     andere
    -2.77
    当然
    -2.48
     anderen
    -2.36
    larda
    -2.34
     다른
    -2.33
    л
    -2.23
    他
    -2.19
     enviable
    -2.13
    现在
    -2.13
    ates
    -2.13
    POSITIVE LOGITS
    geſ
    2.83
    I
    2.72
    );
    2.67
     betrekking
    2.45
    %">
    2.38
     哪
    2.34
     goederen
    2.33
    薆
    2.30
     voorbere
    2.27
    戆
    2.27
    Activations Density 0.001%

    No Known Activations