© 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. 99288
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation

    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
    mainly
    -1.76
    commonly
    -1.64
    became
    -1.64
    becomes
    -1.61
    larg
    -1.59
    tells
    -1.55
    primarily
    -1.55
    despite
    -1.54
    indicated
    -1.53
    basically
    -1.52
    POSITIVE LOGITS
     or
    1.88
     on
    1.58
     extraordinarily
    1.50
     exquisitely
    1.48
     new
    1.48
     without
    1.48
     groundbreaking
    1.47
    =[]
    1.43
     with
    1.37
     impeccable
    1.37
    Activations Density 0.317%

    No Known Activations