© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101517
    Prev
    Next
    INDEX
    Explanations

    to the

    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
     and
    -2.98
     whose
    -2.73
     which
    -2.59
     all
    -2.45
     for
    -2.39
     with
    -2.31
     because
    -2.31
     since
    -2.30
     also
    -2.28
     when
    -2.23
    POSITIVE LOGITS
     unbelievably
    1.92
     revered
    1.74
     poign
    1.71
    ⏑
    1.70
     delightfully
    1.68
    想了想
    1.66
     innumer
    1.66
     hordes
    1.66
     Wirkungen
    1.65
     participer
    1.63
    Activations Density 0.061%

    No Known Activations