© 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. 113783
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
     of
    -1.69
     fallu
    -1.59
    這些
    -1.52
    d
    -1.45
     These
    -1.45
     вместе
    -1.45
     Some
    -1.39
     varandra
    -1.38
    Some
    -1.35
    情況
    -1.34
    POSITIVE LOGITS
    殽
    1.69
    眛
    1.66
    屨
    1.63
     zoude
    1.57
     we
    1.52
     wrze
    1.52
    {
    1.44
    ⩴
    1.39
     绒
    1.38
     dieß
    1.37
    Activations Density 0.018%

    No Known Activations