© 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. 67610
    Prev
    Next
    INDEX
    Explanations

    words containing zer

    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
    阏
    -2.78
     itſelf
    -2.69
     แต่
    -2.59
    珰
    -2.59
    makeat
    -2.55
    colores
    -2.48
    
    -2.47
    莼
    -2.45
     Our
    -2.44
    圌
    -2.44
    POSITIVE LOGITS
    We
    4.00
    0
    3.66
    With
    3.52
    If
    3.28
    It
    3.22
    They
    3.09
    zer
    3.06
    –
    2.91
    This
    2.91
    Now
    2.86
    Activations Density 0.005%

    No Known Activations