© 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. 111880
    Prev
    Next
    INDEX
    Explanations

    accident and its follow-up events

    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
    詎
    -2.52
     вашей
    -2.52
    錞
    -2.45
    
    -2.28
    síða
    -2.25
    ℟
    -2.25
    鶲
    -2.20
    齶
    -2.14
    CONSIN
    -2.13
    〼
    -2.09
    POSITIVE LOGITS
    ↵
    4.03
    g
    2.89
    ↵↵
    2.75
    .
    2.64
     味噌
    2.55
    the
    2.34
    t
    2.33
     sabid
    2.31
    3
    2.27
     convencer
    2.25
    Activations Density 0.011%

    No Known Activations