© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13776
    Prev
    Next
    INDEX
    Explanations

    messed up

    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
    --
    -2.19
     empfohlen
    -1.98
    之为
    -1.94
     zoude
    -1.91
     saludables
    -1.84
    simplified
    -1.81
     afectados
    -1.79
     trám
    -1.78
    twelve
    -1.74
     Brings
    -1.73
    POSITIVE LOGITS
     they
    2.28
     advise
    2.16
     would
    1.83
     природ
    1.77
     what
    1.75
    海鮮
    1.72
    軚
    1.72
     if
    1.72
    Они
    1.71
    の一
    1.70
    Activations Density 0.005%

    No Known Activations