© 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. 59500
    Prev
    Next
    INDEX
    Explanations

    of [noun phrase]

    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
    -1.66
    了过来
    -1.63
     både
    -1.63
    了过去
    -1.61
     ""
    -1.59
    );
    -1.55
    plication
    -1.52
     ‘’
    -1.45
     its
    -1.42
     beide
    -1.41
    POSITIVE LOGITS
     for
    2.02
     in
    1.95
     as
    1.61
     through
    1.56
     написать
    1.52
     with
    1.41
     which
    1.37
     Américas
    1.36
     so
    1.35
    Each
    1.35
    Activations Density 0.198%

    No Known Activations