© 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. 23480
    Prev
    Next
    INDEX
    Explanations

    winger or centre

    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
    駕
    -0.71
     steigt
    -0.70
    させ
    -0.70
     Einfluss
    -0.69
    cerrar
    -0.68
     dict
    -0.68
    μένο
    -0.67
    細節
    -0.67
     spake
    -0.66
    逼
    -0.66
    POSITIVE LOGITS
     winger
    1.25
     wing
    1.16
     wings
    1.00
     Wing
    0.89
     speed
    0.87
    тические
    0.80
     scoring
    0.79
     spectacular
    0.79
     кры
    0.79
    libert
    0.79
    Activations Density 0.025%

    No Known Activations