© 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. 34-GEMMASCOPE-RES-131K
    7. 2842
    Prev
    Next
    INDEX
    Explanations

    bow followed by various word endings

    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_34/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
    風景
    -0.75
     έχει
    -0.72
     $[
    -0.71
    Else
    -0.71
     you
    -0.71
     amer
    -0.70
     Damages
    -0.70
    喱
    -0.70
    itored
    -0.69
     Pak
    -0.68
    POSITIVE LOGITS
     Bow
    1.59
    Bow
    1.52
     bow
    1.36
    bow
    1.27
     BOW
    1.13
     tie
    1.07
    wow
    1.06
     bowing
    1.06
    BOW
    1.02
    lder
    1.01
    Activations Density 0.006%

    No Known Activations