© 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. 85660
    Prev
    Next
    INDEX
    Explanations

    dating, idt, xv, xz

    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
    ܜ
    -2.69
    ↵
    -2.50
    Not
    -2.47
    Using
    -2.36
    韞
    -2.34
    Because
    -2.19
    dération
    -2.16
    Maybe
    -2.14
    With
    -2.13
    Just
    -2.13
    POSITIVE LOGITS
    AutoresizingMask
    2.55
     '
    2.42
    *,
    2.38
    -'
    2.36
     ursprünglich
    2.34
    튿
    2.28
    に来て
    2.22
    眼光
    2.17
     haupts
    2.13
     foremost
    2.11
    Activations Density 0.001%

    No Known Activations