© 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. 75045
    Prev
    Next
    INDEX
    Explanations

    explaining concepts and beginnings

    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
     conferencias
    -1.33
     misiones
    -1.26
     Fähigkeit
    -1.16
     ativos
    -1.16
    我覺得
    -1.15
    Votre
    -1.14
     traducciones
    -1.13
     asociaciones
    -1.10
     nejsou
    -1.09
    tisgarh
    -1.08
    POSITIVE LOGITS
     of
    1.84
     parfüm
    1.26
     siitä
    1.22
    
    1.19
     with
    1.19
     on
    1.17
     bereits
    1.17
    ibility
    1.16
     уже
    1.13
    пора
    1.13
    Activations Density 0.036%

    No Known Activations