© 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. 19855
    Prev
    Next
    INDEX
    Explanations

    Fuj words and horrific 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
    8
    -3.63
    0
    -3.22
    on
    -3.14
    に
    -3.08
    9
    -2.80
     Ensuring
    -2.78
    i
    -2.69
    のは
    -2.69
    c
    -2.67
    A
    -2.67
    POSITIVE LOGITS
    
    2.81
    蟶
    2.80
    錞
    2.63
    
    2.61
    𞤢
    2.56
    泺
    2.53
    ࿆
    2.52
    龊
    2.52
     milestone
    2.48
     gebruikt
    2.45
    Activations Density 0.005%

    No Known Activations