© 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. 10-GEMMASCOPE-RES-131K
    7. 9250
    Prev
    Next
    INDEX
    Explanations

    Riyadh, Magdeburg, Swarovski, Herod

    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_10/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
    This
    -3.30
    It
    -3.25
    e
    -3.08
     It
    -2.84
    ``
    -2.77
    There
    -2.75
    s
    -2.55
    ский
    -2.48
    ...?
    -2.39
    They
    -2.36
    POSITIVE LOGITS
    ſſen
    2.70
    𝕋
    2.52
    翃
    2.50
    ৢ
    2.48
    苹
    2.45
    鶿
    2.44
     炖
    2.44
     solicita
    2.42
     zvuk
    2.41
    
    2.38
    Activations Density 0.015%

    No Known Activations