© 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. 26750
    Prev
    Next
    INDEX
    Explanations

    URLs and hashtags

    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
     bensin
    -1.12
     dagens
    -1.03
    ┬
    -1.02
     ilustracji
    -0.98
     poë
    -0.96
     basa
    -0.96
     streamer
    -0.95
    perfectly
    -0.94
     slike
    -0.94
     grecque
    -0.94
    POSITIVE LOGITS
     #
    1.27
     there
    1.02
     tikai
    0.97
     diminish
    0.93
     (@
    0.92
    ilí
    0.92
     שלנו
    0.91
     scuro
    0.91
    貢献
    0.91
    ኋ
    0.90
    Activations Density 0.008%

    No Known Activations