© 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. 97950
    Prev
    Next
    INDEX
    Explanations

    graphics and on-air presentation

    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
    hsl
    -0.81
    oluene
    -0.81
     Induced
    -0.74
    ósz
    -0.74
    Mona
    -0.73
    dlc
    -0.72
    中学
    -0.72
     SYLLABLE
    -0.71
    Modes
    -0.71
    #*
    -0.71
    POSITIVE LOGITS
     graphics
    2.28
     graphic
    1.84
     Graphics
    1.66
    graphics
    1.56
    Graphics
    1.53
     Graphic
    1.45
    Graphic
    1.40
     graphical
    1.39
    graphic
    1.34
    GRAPHICS
    1.30
    Activations Density 0.034%

    No Known Activations