© 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. 87252
    Prev
    Next
    INDEX
    Explanations

    here and its context

    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
     your
    -1.77
     motivadoras
    -1.63
    怎么回事
    -1.55
    现在的
    -1.38
    ݮ
    -1.37
    udadera
    -1.36
    jelen
    -1.35
     vuestra
    -1.35
     amables
    -1.35
     verdaderas
    -1.34
    POSITIVE LOGITS
     of
    2.38
    嫖
    1.44
     in
    1.34
     '-';
    1.34
    偷偷
    1.34
    lamine
    1.33
    citet
    1.32
    raux
    1.32
     sebaik
    1.32
     '=',
    1.31
    Activations Density 0.025%

    No Known Activations