© 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. 34-GEMMASCOPE-RES-131K
    7. 30484
    Prev
    Next
    INDEX
    Explanations

    its affiliates

    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_34/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
    cheiben
    -0.98
     framework
    -0.88
     Zähne
    -0.86
     Corollary
    -0.85
     โดย
    -0.83
     vyt
    -0.82
     ehemal
    -0.82
     increase
    -0.81
     uzav
    -0.78
     тот
    -0.77
    POSITIVE LOGITS
     heilig
    1.04
     or
    1.02
     gange
    1.02
    在美国
    1.00
     afstand
    0.99
    的其他
    0.97
     amerik
    0.95
     blik
    0.95
     ovale
    0.93
     sosi
    0.92
    Activations Density 0.052%

    No Known Activations