© 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. 26141
    Prev
    Next
    INDEX
    Explanations

    word and phrase completion

    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
     it
    -1.12
    ********/
    -1.08
     other
    -0.98
    并在
    -0.95
     känner
    -0.92
    Lá
    -0.91
    Ukra
    -0.88
    ственными
    -0.88
    (=)
    -0.87
    
    -0.86
    POSITIVE LOGITS
     lumineuse
    0.99
     Abbé
    0.98
    Someone
    0.97
    ङ
    0.96
    ता
    0.95
     chré
    0.95
    '
    0.94
     слой
    0.94
    不过是
    0.94
     Valentín
    0.94
    Activations Density 0.028%

    No Known Activations