© 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. 34-GEMMASCOPE-RES-131K
    4. 55943
    Prev
    Next
    INDEX
    Explanations

    Apache License Version 2.0

    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_34/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
     ashamed
    -0.67
    ders
    -0.67
    complement
    -0.66
     by
    -0.66
     шпа
    -0.63
     DISTRICT
    -0.62
     going
    -0.61
     представля
    -0.61
    éton
    -0.60
    躇
    -0.60
    POSITIVE LOGITS
    émy
    0.77
    を迎
    0.77
     circo
    0.74
     mrt
    0.73
    BASED
    0.73
    тических
    0.71
    obacteria
    0.70
    Routine
    0.70
    grafi
    0.70
    grafo
    0.69
    Activations Density 0.041%

    No Known Activations