© 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. 67759
    Prev
    Next
    INDEX
    Explanations

    names in crime contexts

    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
     vôtre
    -1.58
     magasiner
    -1.52
    槤
    -1.50
     territoriale
    -1.48
    も多い
    -1.44
     visse
    -1.38
     meub
    -1.38
     kérd
    -1.37
    توض
    -1.37
     сьогодні
    -1.36
    POSITIVE LOGITS
     who
    2.28
     which
    1.48
     whom
    1.45
    ที่
    1.38
     was
    1.29
    who
    1.27
     on
    1.26
     «
    1.23
    which
    1.20
     whose
    1.20
    Activations Density 0.071%

    No Known Activations