© 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. 38635
    Prev
    Next
    INDEX
    Explanations

    lived experience of

    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
     assemblage
    -0.76
     tincture
    -0.66
    sied
    -0.66
    Prensa
    -0.65
     possibilità
    -0.63
     Conway
    -0.63
     Assemb
    -0.63
    gruppen
    -0.63
    곤
    -0.61
    ứa
    -0.60
    POSITIVE LOGITS
     kaldır
    0.73
    իկ
    0.68
    VARIANT
    0.68
    лос
    0.67
     reson
    0.67
     furnace
    0.66
     larceny
    0.66
    敌
    0.65
     Furnace
    0.65
    giá
    0.65
    Activations Density 0.080%

    No Known Activations