© 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. 22-GEMMASCOPE-RES-131K
    7. 72439
    Prev
    Next
    INDEX
    Explanations

    foreign political and legal entities

    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_22/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
     oiseau
    -0.97
     decisivo
    -0.96
     espoir
    -0.89
     downvoted
    -0.88
    жку
    -0.88
     asshole
    -0.88
     curé
    -0.88
     ancho
    -0.87
     porcelaine
    -0.87
     famoso
    -0.86
    POSITIVE LOGITS
     misguided
    0.91
     this
    0.89
    mbH
    0.88
     bezig
    0.88
     कुछ
    0.87
     meint
    0.85
     m
    0.85
    brunn
    0.85
    ׂ
    0.84
     anstatt
    0.84
    Activations Density 0.053%

    No Known Activations