© 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. 886
    Prev
    Next
    INDEX
    Explanations

    titles and HTML tags

    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
    "},
    -0.95
     näin
    -0.93
     during
    -0.89
     During
    -0.84
    During
    -0.80
    "},
    -0.80
    -0.80
    形势
    -0.79
    ذر
    -0.79
    //:
    -0.79
    POSITIVE LOGITS
    вање
    0.88
     proximité
    0.85
    quien
    0.81
     Associations
    0.80
     especialmente
    0.77
     에
    0.76
    emples
    0.76
    掌控
    0.75
     IFF
    0.74
    écu
    0.74
    Activations Density 0.005%

    No Known Activations