© 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. 57391
    Prev
    Next
    INDEX
    Explanations

    signing up

    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
    .
    -1.70
    鱨
    -1.69
     louer
    -1.64
     estadounid
    -1.53
     dì
    -1.52
     last
    -1.51
    盉
    -1.47
     miniaturka
    -1.46
    几十
    -1.45
    -1.41
    POSITIVE LOGITS
     is
    2.14
    With
    1.73
     it
    1.67
     With
    1.63
    These
    1.60
    <bos>
    1.57
    While
    1.54
     how
    1.47
     and
    1.45
    There
    1.45
    Activations Density 0.029%

    No Known Activations