© 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. 38129
    Prev
    Next
    INDEX
    Explanations

    floor designations

    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
    큘
    -0.78
    mettre
    -0.73
     callback
    -0.71
     Agora
    -0.71
    rija
    -0.70
    锰
    -0.68
    囑
    -0.68
     Bewertungen
    -0.67
    螂
    -0.67
    깥
    -0.67
    POSITIVE LOGITS
     floor
    5.53
     floors
    5.16
    floor
    4.44
     Floor
    4.34
    Floor
    4.19
    floors
    3.69
     FLOOR
    3.63
     Floors
    3.59
    FLOOR
    3.39
     flooring
    2.52
    Activations Density 0.027%

    No Known Activations