© 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. 90694
    Prev
    Next
    INDEX
    Explanations

    `/guide` links

    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
    QUEEN
    -0.79
     TEM
    -0.78
     μικ
    -0.76
     micros
    -0.75
     Membrane
    -0.74
    สึก
    -0.70
     Cops
    -0.69
    breve
    -0.68
     Micros
    -0.67
     števil
    -0.67
    POSITIVE LOGITS
     estimates
    0.68
    ヤン
    0.66
    notice
    0.66
    RepeatedField
    0.65
    
    0.65
     مرات
    0.64
     estético
    0.63
     Мария
    0.63
    lera
    0.63
    ystems
    0.62
    Activations Density 0.071%

    No Known Activations