© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13644
    Prev
    Next
    INDEX
    Explanations

    body parts in action

    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
     that
    -1.67
     such
    -1.28
     there
    -1.28
     it
    -1.22
    ability
    -1.20
     than
    -1.16
     consideración
    -1.13
    وص
    -1.06
     consideration
    -1.05
     solchen
    -1.05
    POSITIVE LOGITS
     τὰ
    1.05
     közé
    1.01
     листь
    0.97
    newspaper
    0.94
    🎼
    0.94
     Kommune
    0.94
    Following
    0.94
     infanti
    0.93
    খন
    0.91
     известных
    0.91
    Activations Density 0.008%

    No Known Activations