© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    shot fired

    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_10/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
     annons
    -1.52
     totalt
    -1.48
     äls
    -1.22
     natten
    -1.21
     förra
    -1.21
     egent
    -1.20
     utom
    -1.19
     kvinna
    -1.16
     illustrationer
    -1.16
     steg
    -1.16
    POSITIVE LOGITS
     traditionelle
    1.41
    AIRE
    1.33
     aDecoder
    1.31
    ériale
    1.30
     professionelle
    1.28
     Soporte
    1.25
     originalen
    1.25
     kenyataan
    1.23
    ',
    1.23
     Réalisation
    1.20
    Activations Density 0.026%

    No Known Activations