© 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. 98
    Prev
    Next
    INDEX
    Explanations

    numbers and roman numerals followed by commas or letters

    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
    -1.79
     you
    -1.72
     even
    -1.65
    c
    -1.55
    f
    -1.48
    s
    -1.46
    ly
    -1.46
     there
    -1.43
    w
    -1.41
    b
    -1.38
    POSITIVE LOGITS
    </strong>
    1.69
     cortada
    1.66
    lepší
    1.63
    ambut
    1.63
    islamic
    1.61
    när
    1.59
    notre
    1.56
    garmin
    1.55
    motorola
    1.54
    gabung
    1.53
    Activations Density 0.062%

    No Known Activations