© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71140
    Prev
    Next
    INDEX
    Explanations

    3rd Low Altitude Air Defense Battalion

    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
     coûts
    -1.05
     ralenti
    -1.04
     précip
    -1.04
     fournisseurs
    -1.03
    ressional
    -1.02
    יבור
    -1.02
     éta
    -1.00
    뻣
    -0.98
     immédiatement
    -0.98
     éte
    -0.98
    POSITIVE LOGITS
    </em>
    1.09
     related
    0.88
    <
    0.86
     all
    0.86
     exceptions
    0.84
     b
    0.83
    こうした
    0.83
     non
    0.82
     B
    0.80
     (
    0.80
    Activations Density 0.082%

    No Known Activations