© 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. 84674
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    蚱
    -1.63
     HAVING
    -1.52
    Ș
    -1.50
     blatant
    -1.49
    tych
    -1.45
     gangguan
    -1.45
    趿
    -1.42
    坶
    -1.42
     dwóch
    -1.41
     luscious
    -1.41
    POSITIVE LOGITS
     like
    1.94
     your
    1.84
     only
    1.80
    The
    1.76
    If
    1.70
    just
    1.70
     embodies
    1.63
     despite
    1.54
     for
    1.49
     just
    1.48
    Activations Density 0.085%

    No Known Activations