© 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. 98422
    Prev
    Next
    INDEX
    Explanations

    railway station

    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
     realizacji
    -0.88
     unnecessary
    -0.79
     Einstellungen
    -0.79
    ̡
    -0.78
     Commentaires
    -0.78
     зелены
    -0.77
    testimonial
    -0.77
     ladr
    -0.77
    Unexpected
    -0.75
     Kartoffeln
    -0.75
    POSITIVE LOGITS
     Richt
    0.85
     archite
    0.81
     Cheapest
    0.81
     Colgate
    0.80
     Flies
    0.80
    ït
    0.78
     hourly
    0.78
    昧
    0.78
     Avian
    0.76
    かし
    0.76
    Activations Density 0.006%

    No Known Activations