© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8453
    Prev
    Next
    INDEX
    Explanations

    the word reads

    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
    f
    -3.47
    a
    -3.38
    ed
    -3.05
    ing
    -3.03
    ा
    -2.89
    d
    -2.81
    u
    -2.75
    c
    -2.70
    ro
    -2.64
    i
    -2.59
    POSITIVE LOGITS
    谖
    2.61
    
    2.58
    
    2.47
    真心
    2.41
    絝
    2.36
     reads
    2.34
     juzg
    2.33
    CurtirCurtir
    2.30
     espet
    2.30
    で
    2.27
    Activations Density 0.003%

    No Known Activations