© 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. 22-GEMMASCOPE-RES-131K
    7. 14970
    Prev
    Next
    INDEX
    Explanations

    error assignment in code

    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_22/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
     détente
    -1.05
    moderne
    -1.04
    prek
    -1.02
     achat
    -0.97
     opérés
    -0.94
     ventes
    -0.93
     romaine
    -0.93
    ครื่อง
    -0.93
     accepter
    -0.93
     vider
    -0.93
    POSITIVE LOGITS
     first
    1.38
     if
    1.12
     before
    1.09
     may
    1.09
     can
    1.06
     go
    1.05
     from
    1.05
     only
    1.04
     actually
    0.99
    &
    0.96
    Activations Density 0.002%

    No Known Activations