© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47665
    Prev
    Next
    INDEX
    Explanations

    news headlines and identifiers

    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
    0
    -3.73
    -“
    -3.44
    -”
    -3.13
    —”
    -2.97
     helg
    -2.95
    ‘
    -2.91
    6
    -2.77
    $
    -2.70
    
    -2.69
     plastico
    -2.66
    POSITIVE LOGITS
     "
    3.97
     are
    3.42
     '
    3.06
     ''
    2.63
    炜
    2.48
    }$
    2.45
     céle
    2.45
     "'
    2.42
     ("
    2.41
    )$
    2.38
    Activations Density 0.000%

    No Known Activations