© 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. 22-GEMMASCOPE-RES-131K
    7. 130237
    Prev
    Next
    INDEX
    Explanations

    browsers and operating systems

    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
    為に
    -1.48
    m
    -1.41
    S
    -1.33
    낸
    -1.30
    r
    -1.30
    f
    -1.28
     ioutil
    -1.27
    aters
    -1.25
     even
    -1.25
    ons
    -1.24
    POSITIVE LOGITS
    bánh
    1.48
    Lá
    1.46
    や
    1.43
    Karakter
    1.38
    Audiobook
    1.38
    を設置
    1.33
    は
    1.30
    COMO
    1.30
    Recept
    1.30
    があり
    1.27
    Activations Density 0.004%

    No Known Activations