© 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. 107273
    Prev
    Next
    INDEX
    Explanations

    coordinates and transformations

    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
    asje
    -0.77
    ienė
    -0.77
    favourable
    -0.76
    profitable
    -0.74
    createTime
    -0.71
     Berat
    -0.70
    パク
    -0.70
    PrototypeOf
    -0.68
     potenci
    -0.68
    Replacement
    -0.68
    POSITIVE LOGITS
     world
    1.25
     pixel
    1.23
     converted
    1.16
     converts
    1.16
     relative
    1.16
     transformed
    1.14
    world
    1.13
    relative
    1.13
     converting
    1.11
     converters
    1.09
    Activations Density 0.023%

    No Known Activations