© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7701
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation

    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
    '
    -2.17
    -
    -2.03
    ,
    -1.68
    sisting
    -1.54
    了一些
    -1.48
    制的
    -1.45
     expanse
    -1.41
    2
    -1.41
    着一个
    -1.40
    I
    -1.40
    POSITIVE LOGITS
    咴
    2.33
     protože
    1.78
     juft
    1.77
    舠
    1.69
     corretto
    1.69
     triliun
    1.67
     nahil
    1.66
     havaianas
    1.65
    attes
    1.60
     legislat
    1.55
    Activations Density 0.008%

    No Known Activations