© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1556
    Prev
    Next
    INDEX
    Explanations

    factor, group, subset, list, data.frame

    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
    snr
    -0.76
    トヨタ
    -0.76
    граммы
    -0.73
    ép
    -0.73
    nikami
    -0.70
     nouveautés
    -0.69
    
    -0.69
    良いです
    -0.68
    '&:
    -0.68
    
    -0.68
    POSITIVE LOGITS
     factor
    1.02
    factor
    0.93
    factors
    0.85
     Factors
    0.84
     Factor
    0.84
    Factors
    0.84
     factors
    0.80
     facteur
    0.77
    reshape
    0.77
     Said
    0.76
    Activations Density 0.090%

    No Known Activations