© 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. 59682
    Prev
    Next
    INDEX
    Explanations

    deep space

    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
    蜃
    -0.79
    ungszeit
    -0.75
    ksiä
    -0.75
    mā
    -0.73
     Nicolai
    -0.73
    maison
    -0.72
    sunami
    -0.71
     hydra
    -0.71
     Gras
    -0.70
    টি
    -0.70
    POSITIVE LOGITS
     space
    3.56
    space
    2.67
     Space
    2.50
     SPACE
    2.28
    Space
    2.27
    空间
    2.25
     espacio
    2.14
    空間
    2.13
    SPACE
    2.11
     espaço
    2.00
    Activations Density 0.029%

    No Known Activations