© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29054
    Prev
    Next
    INDEX
    Explanations

    The present

    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
     rezept
    -1.55
    Offic
    -1.55
    nellement
    -1.46
    我们会
    -1.46
    ‾
    -1.45
     renom
    -1.42
    ‍♂️
    -1.41
     perfe
    -1.39
     squadra
    -1.38
     alfo
    -1.36
    POSITIVE LOGITS
     لأنه
    1.70
     шесть
    1.69
     is
    1.63
    6
    1.57
    larını
    1.55
     increasingly
    1.54
     прошлом
    1.52
     tendrá
    1.51
     yalnızca
    1.50
     hinzugefügt
    1.45
    Activations Density 0.019%

    No Known Activations