© 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. 34-GEMMASCOPE-RES-131K
    7. 49191
    Prev
    Next
    INDEX
    Explanations

    taken into account

    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
     macetas
    -1.09
    ='';
    -1.00
    ="";
    -0.96
     after
    -0.95
     intorno
    -0.93
     بیرون
    -0.92
     ventilación
    -0.92
     mụn
    -0.88
    钝
    -0.88
    いだ
    -0.86
    POSITIVE LOGITS
     in
    2.94
     when
    2.92
    ในการ
    2.83
     dalam
    2.52
     while
    2.31
     lors
    1.96
     to
    1.94
     cuando
    1.87
     during
    1.86
     trong
    1.84
    Activations Density 0.157%

    No Known Activations