© 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. 22-GEMMASCOPE-RES-131K
    7. 65406
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting

    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_22/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
    -1.51
    ִּ
    -1.17
     favorecer
    -1.12
    ֶּ
    -1.12
     year
    -1.12
    ַּ
    -1.12
     age
    -1.09
     ftate
    -1.09
    ּוֹ
    -1.08
    なのだ
    -1.07
    POSITIVE LOGITS
    ἵ
    1.35
     панель
    1.21
     chrétien
    1.20
    ׇ
    1.16
    μένου
    1.16
     sintomas
    1.14
    惊艳
    1.13
     joya
    1.13
     料理
    1.11
    了下去
    1.11
    Activations Density 0.055%

    No Known Activations