© 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. 70213
    Prev
    Next
    INDEX
    Explanations

    names and foreign terms

    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
     kony
    -0.78
     emp
    -0.78
     MEDIUM
    -0.76
     Eren
    -0.75
     keines
    -0.75
     Msg
    -0.73
    
    -0.72
     lubric
    -0.72
     procede
    -0.71
    dée
    -0.71
    POSITIVE LOGITS
    Sa
    0.84
     relates
    0.79
     Breslau
    0.77
     chcia
    0.77
    Caratter
    0.76
    Formerly
    0.71
    caso
    0.71
    Rifer
    0.70
     relate
    0.70
     sinner
    0.69
    Activations Density 0.050%

    No Known Activations