© 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. 98299
    Prev
    Next
    INDEX
    Explanations

    questions or recommendations

    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
    সূ
    -1.27
    през
    -1.23
     매우
    -1.23
     déjeuner
    -1.16
    いただきたい
    -1.15
    
    -1.15
    SUNG
    -1.11
    ﻚ
    -1.11
    ться
    -1.10
    rás
    -1.10
    POSITIVE LOGITS
     various
    1.22
    Tudo
    1.20
     different
    1.13
    Quais
    1.12
     ваго
    1.08
     sodass
    1.05
    Dicas
    1.05
     worauf
    1.05
    Nossa
    1.05
    unków
    1.03
    Activations Density 0.000%

    No Known Activations