© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20614
    Prev
    Next
    INDEX
    Explanations

    answer marker A:

    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
    </strong>
    -2.78
    ௗ
    -1.77
     prolonged
    -1.73
     his
    -1.67
     fotógrafo
    -1.54
     decidiu
    -1.50
    </h1>
    -1.48
     continued
    -1.48
     of
    -1.46
     participó
    -1.44
    POSITIVE LOGITS
    ainen
    1.83
     Anſ
    1.75
    )]);
    1.66
    ConstraintMaker
    1.63
    metries
    1.63
    hancers
    1.63
    ].)
    1.61
    緝
    1.60
    boxylic
    1.58
    ,"%
    1.56
    Activations Density 0.025%

    No Known Activations