© 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. 102936
    Prev
    Next
    INDEX
    Explanations

    Liss, Ober, Bar, Cars

    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
     або
    -0.72
     撮影
    -0.71
    ABASE
    -0.70
    ᵤ
    -0.69
     neither
    -0.68
     lingkungan
    -0.67
    árd
    -0.67
    *****
    -0.67
     qx
    -0.67
     電話
    -0.66
    POSITIVE LOGITS
    iosi
    0.83
    vle
    0.78
     utilisant
    0.76
    higan
    0.73
    eroon
    0.72
     déliv
    0.72
     verificare
    0.72
    entliche
    0.71
    atzen
    0.70
     två
    0.70
    Activations Density 0.167%

    No Known Activations