© 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. 113308
    Prev
    Next
    INDEX
    Explanations

    agent

    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
    ’
    -2.89
    的就
    -2.66
    dámské
    -2.45
    憷
    -2.45
     startling
    -2.44
     ferocious
    -2.44
    歃
    -2.44
     exceptionally
    -2.41
     astonishing
    -2.38
    碰到
    -2.33
    POSITIVE LOGITS
    曁
    2.81
    Since
    2.78
    可以
    2.56
     For
    2.56
    ꒥
    2.52
    Because
    2.50
     podem
    2.48
     interesado
    2.48
    Usually
    2.48
    Shortly
    2.45
    Activations Density 0.019%

    No Known Activations