© 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. 58852
    Prev
    Next
    INDEX
    Explanations

    A:

    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
    -1.70
     is
    -1.66
     These
    -1.52
     has
    -1.44
     would
    -1.41
    <b>
    -1.37
     will
    -1.34
    '
    -1.33
    umpad
    -1.31
     describes
    -1.27
    POSITIVE LOGITS
     SPECIFIC
    1.51
     asla
    1.48
     ANY
    1.46
    箆
    1.45
     概要
    1.45
    璝
    1.44
    γωγ
    1.41
    邃
    1.41
     legyen
    1.41
    otropy
    1.41
    Activations Density 0.063%

    No Known Activations