© 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. 34-GEMMASCOPE-RES-131K
    7. 6867
    Prev
    Next
    INDEX
    Explanations

    Tk inter, spirit of, tissue specific, Slovenian

    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
     BFS
    -0.74
     [_
    -0.73
    Avocado
    -0.71
    Irving
    -0.69
    culous
    -0.69
    Phylogenetic
    -0.68
    addToCart
    -0.67
    atividad
    -0.67
     tracer
    -0.66
     IOP
    -0.66
    POSITIVE LOGITS
     Fiber
    0.81
     glas
    0.79
     glass
    0.79
     Glass
    0.79
    kraut
    0.77
    Glass
    0.75
    glass
    0.73
     fiber
    0.73
    medic
    0.73
    ток
    0.71
    Activations Density 0.040%

    No Known Activations