© 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. 22-GEMMASCOPE-RES-131K
    7. 79891
    Prev
    Next
    INDEX
    Explanations

    role and function

    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
     homicidio
    -1.30
    是怎么回事
    -1.16
     akşam
    -1.16
     betekent
    -1.15
     podría
    -1.10
     terbuat
    -1.10
     pertenece
    -1.09
     jueves
    -1.06
     descubre
    -1.06
     Preferencias
    -1.05
    POSITIVE LOGITS
    parece
    1.15
     noms
    1.12
    olesterol
    1.12
     plupart
    1.07
    曲は
    1.06
     Maître
    1.04
    搅拌
    1.03
    nexo
    1.02
     クリック
    1.01
    茄
    1.00
    Activations Density 0.076%

    No Known Activations