© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12931
    Prev
    Next
    INDEX
    Explanations

    making something

    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
    obtained
    -1.60
    我們
    -1.57
     know
    -1.48
    了她
    -1.47
     when
    -1.47
    ↴
    -1.43
    larımız
    -1.43
    ances
    -1.41
    s
    -1.41
    ⦊
    -1.41
    POSITIVE LOGITS
     a
    1.78
    création
    1.59
     腿
    1.53
     Somewhat
    1.41
    ednesday
    1.41
     Picchu
    1.39
    ători
    1.38
     presque
    1.36
    一个小
    1.36
     fréquemment
    1.35
    Activations Density 0.067%

    No Known Activations