© 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. 188
    Prev
    Next
    INDEX
    Explanations

    phrases separated by commas

    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
     and
    -1.99
     jugó
    -1.56
    🤛
    -1.47
    dịch
    -1.44
     ect
    -1.41
    )'
    -1.40
     :"
    -1.40
    蛲
    -1.39
     возможность
    -1.37
    saya
    -1.37
    POSITIVE LOGITS
     вами
    1.80
    émoc
    1.63
     Что
    1.58
    縢
    1.52
     our
    1.48
    cetamol
    1.47
     behandeln
    1.47
    from
    1.46
    ୬
    1.44
    ibrill
    1.41
    Activations Density 0.294%

    No Known Activations