© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    tiff pages

    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
     Xiong
    -0.78
     SEQ
    -0.76
     manier
    -0.74
    oric
    -0.73
     Busch
    -0.72
    ayanan
    -0.70
     ISNI
    -0.70
    ierung
    -0.70
     Clancy
    -0.69
     Rubio
    -0.69
    POSITIVE LOGITS
     Baseline
    0.98
     Strip
    0.91
     strips
    0.88
     strip
    0.86
    Baseline
    0.79
     Strips
    0.79
    Strip
    0.77
     fax
    0.74
     къ
    0.73
    Predict
    0.70
    Activations Density 0.020%

    No Known Activations