© 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. 72108
    Prev
    Next
    INDEX
    Explanations

    error throwing and result handling

    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
     pájaro
    -1.17
     celta
    -1.17
     épu
    -1.15
     anjo
    -1.15
     rajut
    -1.14
    窸
    -1.13
    Тел
    -1.08
     menino
    -1.07
     sés
    -1.07
     unicórnio
    -1.05
    POSITIVE LOGITS
     but
    1.23
    return
    1.23
     result
    0.98
    结果
    0.96
     e
    0.95
    sete
    0.93
    se
    0.91
     Grüßen
    0.90
    si
    0.90
     ولم
    0.90
    Activations Density 0.001%

    No Known Activations