© 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. 40299
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or 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
     to
    -1.61
     warum
    -1.44
     satisfe
    -1.43
     those
    -1.41
     same
    -1.35
     мелки
    -1.31
    ೣ
    -1.29
     kde
    -1.27
    ;">
    -1.27
    +}$
    -1.25
    POSITIVE LOGITS
    '
    1.91
     estrena
    1.23
     teatral
    1.22
     EXACTLY
    1.20
     maakte
    1.20
    🕗
    1.20
    (?)
    1.19
     intere
    1.18
     ‘’
    1.18
    You
    1.18
    Activations Density 0.043%

    No Known Activations