© 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. 10-GEMMASCOPE-RES-131K
    7. 69876
    Prev
    Next
    INDEX
    Explanations

    answer accepted

    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_10/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
    
    -1.95
    endimiento
    -1.63
    ’，
    -1.59
     éven
    -1.57
     podemos
    -1.55
    ſtra
    -1.55
    edil
    -1.54
     PUSTAKA
    -1.53
    ʯ
    -1.50
     alguns
    -1.48
    POSITIVE LOGITS
    ↵↵
    2.30
    us
    2.11
    no
    2.08
    In
    1.95
    ia
    1.80
    B
    1.76
     answers
    1.74
    Data
    1.70
    This
    1.70
    ss
    1.68
    Activations Density 0.035%

    No Known Activations