© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87265
    Prev
    Next
    INDEX
    Explanations

    beard-related descriptions

    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
     bygger
    -0.86
    rages
    -0.75
     degree
    -0.75
     HUGH
    -0.74
    Pol
    -0.74
     Rizal
    -0.73
    rucks
    -0.73
     Pá
    -0.71
    yon
    -0.70
    جر
    -0.70
    POSITIVE LOGITS
     frecuentemente
    0.77
     eléctrico
    0.76
    erto
    0.73
    合わせた
    0.73
     необ
    0.71
     expecting
    0.70
    cbe
    0.70
    CADE
    0.69
    Apparatus
    0.68
    utusan
    0.67
    Activations Density 0.014%

    No Known Activations