© 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. 44700
    Prev
    Next
    INDEX
    Explanations

    visual properties for plots

    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
     such
    -1.40
     décider
    -1.30
     eſt
    -1.30
    Ưu
    -1.29
     wtedy
    -1.29
     müm
    -1.29
     kategor
    -1.23
     önem
    -1.22
     discípulos
    -1.21
     öde
    -1.20
    POSITIVE LOGITS
    abbaye
    1.29
     each
    1.28
    פּ
    1.27
     at
    1.27
    ֙
    1.26
     ||
    1.24
     refroidissement
    1.24
    ;">
    1.16
    ὲν
    1.16
    כשיו
    1.15
    Activations Density 0.069%

    No Known Activations