© 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. 39694
    Prev
    Next
    INDEX
    Explanations

    the followed by specific entities

    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
     was
    -3.19
    螣
    -2.56
     THEM
    -2.55
    fordshire
    -2.38
    ↑↑↑</
    -2.30
    柃
    -2.28
     meestal
    -2.25
    ificantly
    -2.23
     nooit
    -2.20
    禵
    -2.20
    POSITIVE LOGITS
    There
    3.13
    the
    2.78
    They
    2.70
    The
    2.58
    You
    2.56
    It
    2.48
     pleasures
    2.48
    Your
    2.42
     damski
    2.41
     españolas
    2.41
    Activations Density 0.031%

    No Known Activations