© 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. 102511
    Prev
    Next
    INDEX
    Explanations

    monument and monumental structures

    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
     Kiedy
    -2.47
     Dlatego
    -2.41
     unſ
    -2.33
     moglie
    -2.31
     leaſt
    -2.25
     Może
    -2.22
     сист
    -2.20
    ⣞
    -2.20
    Контак
    -2.19
     quirks
    -2.19
    POSITIVE LOGITS
    ↵
    4.22
    '
    3.36
    <em>
    3.09
     
    3.03
     silencioso
    2.50
    ︲
    2.39
     "
    2.39
    虽说
    2.38
    —
    2.34
    のお話
    2.30
    Activations Density 0.001%

    No Known Activations