© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48458
    Prev
    Next
    INDEX
    Explanations

    vocal formations

    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
     حرف
    -0.87
    (({
    -0.84
    baca
    -0.78
     வி
    -0.77
     Bogotá
    -0.77
    maksi
    -0.76
    owany
    -0.76
     näin
    -0.74
    믿
    -0.73
     ganzen
    -0.73
    POSITIVE LOGITS
     cords
    1.44
    izations
    1.27
    ists
    1.17
     cord
    1.11
    isation
    1.05
     chords
    0.96
    ising
    0.94
    izing
    0.93
    ises
    0.92
    cord
    0.88
    Activations Density 0.010%

    No Known Activations