© 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. 9853
    Prev
    Next
    INDEX
    Explanations

    python os module

    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
     that
    -1.50
     потому
    -1.31
     possono
    -1.30
     from
    -1.28
     those
    -1.27
     our
    -1.23
     pueden
    -1.23
     chá
    -1.19
     jotka
    -1.18
     such
    -1.17
    POSITIVE LOGITS
    Another
    1.52
     Another
    1.50
    Your
    1.49
     name
    1.42
    You
    1.35
    gemeen
    1.35
    another
    1.34
    你的
    1.31
    Trying
    1.30
    cyklo
    1.30
    Activations Density 0.026%

    No Known Activations