© 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. 33589
    Prev
    Next
    INDEX
    Explanations

    American Legion Tournament

    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
    truncated
    -0.75
     武
    -0.69
     процедуры
    -0.68
     systemic
    -0.66
    ệnh
    -0.66
     Linked
    -0.66
    清理
    -0.66
    TRAINING
    -0.65
     Nil
    -0.65
     Catholic
    -0.65
    POSITIVE LOGITS
    TERS
    0.81
     volunteers
    0.80
     sleep
    0.79
    '}),
    0.78
     Organizador
    0.78
    énus
    0.78
    ]=(
    0.78
    🗺
    0.78
     Tenor
    0.77
    INTERNATIONAL
    0.76
    Activations Density 0.010%

    No Known Activations