© 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. 22-GEMMASCOPE-RES-131K
    7. 66049
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers

    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_22/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
    <bos>
    -1.23
     with
    -1.10
    When
    -1.08
     substantially
    -1.05
    で
    -0.98
    もしか
    -0.98
     pembuatan
    -0.97
    や
    -0.97
     for
    -0.96
     changes
    -0.96
    POSITIVE LOGITS
     None
    1.02
    issent
    0.96
     tof
    0.95
     интервью
    0.94
     châ
    0.94
     iban
    0.92
    のですか
    0.91
    たびに
    0.91
    geste
    0.91
    haltet
    0.90
    Activations Density 0.029%

    No Known Activations