© 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. 128396
    Prev
    Next
    INDEX
    Explanations

    spasm, phenomenological, phenomenal

    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
    "
    -3.13
    地面
    -2.78
    は
    -2.77
    НОЙ
    -2.41
    !?
    -2.39
    さんの
    -2.30
     vostre
    -2.30
    ᚷ
    -2.28
    犯罪
    -2.27
    人の
    -2.25
    POSITIVE LOGITS
     noting
    2.48
    –
    2.44
    
    2.28
    くちゃ
    2.25
    みたいです
    2.22
    _
    2.09
    比如说
    2.06
    同时也
    1.94
    这也是
    1.92
    喜歡的
    1.92
    Activations Density 0.009%

    No Known Activations