© 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. 9300
    Prev
    Next
    INDEX
    Explanations

    metry measurements

    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
    '
    -4.06
    2
    -3.30
    4
    -2.75
    7
    -2.70
    w
    -2.67
    8
    -2.67
    g
    -2.58
    ing
    -2.56
    Of
    -2.52
    5
    -2.45
    POSITIVE LOGITS
     aqueles
    2.33
    翃
    2.22
     bús
    2.19
    酩
    2.16
     suporta
    2.14
     ligar
    2.14
    อื่น
    2.14
    砹
    2.11
    顰
    2.11
     otros
    2.11
    Activations Density 0.026%

    No Known Activations