© 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. 7267
    Prev
    Next
    INDEX
    Explanations

    completing names and phrases

    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
    -2.75
     with
    -2.16
     in
    -2.03
     помощью
    -1.81
     tells
    -1.66
     began
    -1.60
     through
    -1.59
     enhance
    -1.58
     took
    -1.57
     or
    -1.51
    POSITIVE LOGITS
    袛
    2.02
    .《
    1.93
     alluring
    1.86
    vaila
    1.86
    っているので
    1.83
    The
    1.80
     They
    1.78
    亊
    1.76
     nimi
    1.74
     about
    1.73
    Activations Density 0.000%

    No Known Activations