© 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. 1375
    Prev
    Next
    INDEX
    Explanations

    the case incident agreement accident collision

    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
     maniere
    -1.47
     THEIR
    -1.34
     formid
    -1.33
     crucial
    -1.33
    Iam
    -1.32
    nende
    -1.31
     スクエア
    -1.31
     innumer
    -1.30
    </u>
    -1.30
    ほんと
    -1.29
    POSITIVE LOGITS
     because
    1.95
     has
    1.94
     had
    1.90
     as
    1.82
     just
    1.79
     two
    1.70
     several
    1.70
     and
    1.69
     completely
    1.65
     longstanding
    1.61
    Activations Density 0.046%

    No Known Activations