© 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. 69348
    Prev
    Next
    INDEX
    Explanations

    catalog entry

    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
     ſou
    -3.09
     soñ
    -3.00
    炱
    -2.78
     konkrét
    -2.75
     ſever
    -2.69
    阗
    -2.67
    薷
    -2.66
    ⾒
    -2.63
    rália
    -2.56
     filozof
    -2.52
    POSITIVE LOGITS
    ]
    5.19
    ”
    3.45
    {
    3.11
    Y
    3.11
    to
    3.09
    n
    3.09
    m
    3.05
    a
    3.05
    as
    3.03
     {
    2.97
    Activations Density 0.002%

    No Known Activations