© 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. 128674
    Prev
    Next
    INDEX
    Explanations

    code test markers

    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
     will
    -2.33
     should
    -2.13
     have
    -2.11
     who
    -1.99
     was
    -1.98
     at
    -1.82
     has
    -1.80
     cannot
    -1.74
     also
    -1.74
     seems
    -1.73
    POSITIVE LOGITS
     organisme
    2.14
     chirurgie
    2.13
     maniere
    2.08
     plafon
    2.05
     faciliter
    1.92
     robuste
    1.90
     rése
    1.88
     autonomie
    1.88
     abonnement
    1.87
     conster
    1.85
    Activations Density 0.052%

    No Known Activations