© 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. 92667
    Prev
    Next
    INDEX
    Explanations

    CGRectMake coordinates

    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
     that
    -1.08
     anyone
    -0.89
    そのため
    -0.88
     certainly
    -0.85
     xấu
    -0.81
     their
    -0.78
     Schluss
    -0.77
     Anyone
    -0.77
     That
    -0.76
     continued
    -0.75
    POSITIVE LOGITS
    BORDER
    1.04
     ۰
    1.01
    margin
    1.01
    MARGIN
    0.98
     صفر
    0.97
     zero
    0.94
     margin
    0.91
    Margin
    0.90
     Margin
    0.89
    BorderSize
    0.89
    Activations Density 0.022%

    No Known Activations