© 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. 22155
    Prev
    Next
    INDEX
    Explanations

    physics symbols and equations

    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
    bluza
    -1.46
    跸
    -1.45
     about
    -1.43
     our
    -1.41
     terwijl
    -1.40
    ৹
    -1.38
     somewhere
    -1.34
     something
    -1.34
     producten
    -1.34
    蛩
    -1.30
    POSITIVE LOGITS
    Another
    1.48
    !
    1.43
     båda
    1.41
    Two
    1.34
    Like
    1.23
    If
    1.21
    ztes
    1.21
    One
    1.17
    What
    1.16
    with
    1.15
    Activations Density 0.019%

    No Known Activations