© 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. 15123
    Prev
    Next
    INDEX
    Explanations

    involved in participation

    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
     parcourir
    -1.14
     znajdu
    -1.11
     installé
    -1.10
     remplacé
    -1.10
    łeś
    -1.10
     reemplazo
    -1.09
     vertraut
    -1.09
     livré
    -1.09
     tramonto
    -1.08
     zewnętr
    -1.05
    POSITIVE LOGITS
     in
    1.83
    参与
    1.41
     mukaan
    1.36
    particip
    1.30
     suç
    1.24
     participation
    1.23
     partecip
    1.22
    Ruben
    1.20
     participa
    1.19
    involved
    1.19
    Activations Density 0.026%

    No Known Activations