© 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. 86638
    Prev
    Next
    INDEX
    Explanations

    obligation or necessity

    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
     one
    -1.34
    б
    -1.24
    .
    -1.15
     campes
    -1.14
    ・・・」
    -1.14
    وفق
    -1.13
     greatly
    -1.12
    One
    -1.10
    IEFS
    -1.09
     automatically
    -1.08
    POSITIVE LOGITS
     to
    1.89
     be
    1.71
     机械
    1.48
     обязательно
    1.48
    edere
    1.46
    raulic
    1.43
     哪些
    1.41
    才可以
    1.32
    emand
    1.31
     luscious
    1.30
    Activations Density 1.001%

    No Known Activations