© 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. 67425
    Prev
    Next
    INDEX
    Explanations

    if followed by explanation

    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
     dança
    -1.62
     Bearbeit
    -1.49
     aprobó
    -1.48
     deterioro
    -1.48
    asnya
    -1.46
    ﻡ
    -1.46
     ähnlichen
    -1.45
    voer
    -1.44
    蕺
    -1.43
     schwier
    -1.41
    POSITIVE LOGITS
     you
    2.80
    If
    1.63
     If
    1.48
     they
    1.38
    !
    1.38
     Considering
    1.35
    2
    1.33
     вслед
    1.30
    $
    1.30
    あなたが
    1.27
    Activations Density 0.014%

    No Known Activations