© 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. 67740
    Prev
    Next
    INDEX
    Explanations

    100%

    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
    5
    -1.86
    7
    -1.80
    3
    -1.80
    稍微
    -1.75
    8
    -1.74
     affitto
    -1.74
    毉
    -1.70
     понадоби
    -1.66
    时的
    -1.64
    9
    -1.64
    POSITIVE LOGITS
     a
    1.98
     of
    1.83
    飏
    1.52
     семьи
    1.48
     gruppe
    1.48
     vores
    1.45
     beker
    1.44
    🏦
    1.43
     both
    1.38
    ically
    1.38
    Activations Density 0.016%

    No Known Activations