© 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. 128393
    Prev
    Next
    INDEX
    Explanations

    follows

    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
    e
    -3.28
    {
    -3.13
    鯪
    -2.94
    ſam
    -2.91
    昃
    -2.64
    廋
    -2.55
    ophageal
    -2.52
     декабря
    -2.41
    鱟
    -2.41
    ꪔ
    -2.38
    POSITIVE LOGITS
     
    3.50
     Then
    3.20
     Each
    3.06
    It
    2.92
     Could
    2.73
    There
    2.70
     Again
    2.61
    独特
    2.61
     Finally
    2.61
    They
    2.59
    Activations Density 0.003%

    No Known Activations