© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30629
    Prev
    Next
    INDEX
    Explanations

    independent or correlated

    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
    ΟΣ
    -0.76
     Messenger
    -0.76
    hadores
    -0.75
     Quill
    -0.75
    ZONE
    -0.74
     tạp
    -0.73
    RIP
    -0.72
    athi
    -0.71
    uesia
    -0.71
     emigrated
    -0.71
    POSITIVE LOGITS
     correlated
    3.89
     correlation
    3.69
    correlated
    3.63
     correlations
    3.47
    Correlation
    3.22
    correlation
    3.14
     Correlation
    3.13
     Correlations
    2.67
     correlate
    2.48
     correl
    2.34
    Activations Density 0.081%

    No Known Activations