© 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. 76212
    Prev
    Next
    INDEX
    Explanations

    maturation as

    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
    currentIndex
    -0.75
    зом
    -0.72
    calciatore
    -0.72
    rfloor
    -0.72
    ൌ
    -0.71
    tés
    -0.71
    قر
    -0.70
     pretentious
    -0.70
     Automobile
    -0.69
     ഉ
    -0.69
    POSITIVE LOGITS
     stoi
    0.74
    sponsor
    0.73
     COU
    0.72
    ゝ
    0.70
     fits
    0.69
    spotify
    0.68
    pest
    0.68
     sponsor
    0.67
     skirt
    0.67
     рассказ
    0.66
    Activations Density 0.042%

    No Known Activations