© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85786
    Prev
    Next
    INDEX
    Explanations

    children at risk

    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
    啐
    -1.47
    '
    -1.42
    莛
    -1.40
     bleue
    -1.38
     wied
    -1.35
    to
    -1.34
    撂
    -1.31
    𓁹
    -1.30
     Feeling
    -1.29
    𓆏
    -1.28
    POSITIVE LOGITS
     by
    2.09
    蒟
    1.59
     since
    1.57
    Beskrivning
    1.56
     เพราะ
    1.50
     without
    1.49
    Achter
    1.44
     until
    1.44
     whose
    1.43
     from
    1.39
    Activations Density 0.102%

    No Known Activations