© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107441
    Prev
    Next
    INDEX
    Explanations

    tangent vectors and geometric spaces

    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
    ឱ
    -0.83
     ngayon
    -0.77
    locally
    -0.73
     spesial
    -0.72
    tte
    -0.70
    Slowly
    -0.70
    Requisitos
    -0.69
    Manually
    -0.69
     kapag
    -0.69
     nät
    -0.69
    POSITIVE LOGITS
     tangent
    1.55
     at
    1.14
    tangent
    1.13
     vertical
    0.96
     tangents
    0.94
     cot
    0.91
     Tang
    0.90
     tại
    0.88
    Tangent
    0.88
     horizontal
    0.87
    Activations Density 0.019%

    No Known Activations