© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14421
    Prev
    Next
    INDEX
    Explanations

    at increased risk

    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
    鷙
    -1.46
    nend
    -1.37
     broderie
    -1.36
    ものである
    -1.34
    [>
    -1.33
    ляли
    -1.32
    ᠯ
    -1.31
     Berita
    -1.30
     didat
    -1.27
     persen
    -1.27
    POSITIVE LOGITS
     risk
    2.30
     risks
    1.99
     Risk
    1.84
     gamble
    1.68
     Risks
    1.67
    Risks
    1.54
     chances
    1.52
    risk
    1.48
     risico
    1.47
     verschiedene
    1.46
    Activations Density 0.127%

    No Known Activations