© 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. 124685
    Prev
    Next
    INDEX
    Explanations

    people you know or love

    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
     anledning
    -1.63
    </u>
    -1.57
    ﹐
    -1.52
    躇
    -1.51
    】：
    -1.49
    ième
    -1.48
     écrivain
    -1.44
     namelijk
    -1.44
     fjor
    -1.41
    ︱
    -1.41
    POSITIVE LOGITS
     who
    2.11
     whom
    1.91
     الذين
    1.73
     with
    1.54
     whose
    1.50
    who
    1.46
     the
    1.44
    をしました
    1.42
     stabbing
    1.42
     közül
    1.41
    Activations Density 0.023%

    No Known Activations