© 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. 84458
    Prev
    Next
    INDEX
    Explanations

    geographical capes and points

    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
    Frost
    -0.73
    ẩm
    -0.72
    ourge
    -0.70
     Frost
    -0.69
     упраж
    -0.68
    Сюжет
    -0.67
    Brackets
    -0.67
    雲
    -0.67
     دیکھیے
    -0.66
    illet
    -0.65
    POSITIVE LOGITS
     Cape
    2.53
     cape
    2.42
    Cape
    2.28
     capes
    1.88
     Point
    1.60
     CAPE
    1.57
     promont
    1.42
    岬
    1.39
     Cabo
    1.37
    CAPE
    1.34
    Activations Density 0.057%

    No Known Activations