© 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. 22063
    Prev
    Next
    INDEX
    Explanations

    words starting with Pan

    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
     they
    -3.64
     selben
    -2.66
     him
    -2.52
    更好
    -2.36
    al
    -2.34
    谖
    -2.31
     verwende
    -2.27
     budeme
    -2.27
     зеле
    -2.20
    钡
    -2.16
    POSITIVE LOGITS
    橚
    2.61
    a
    2.56
    .​
    2.36
    Of
    2.36
    Top
    2.33
    ing
    2.25
    ة
    2.25
     ???
    2.11
     he
    2.09
     sebagai
    2.09
    Activations Density 0.005%

    No Known Activations