© 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. 34-GEMMASCOPE-RES-131K
    7. 49204
    Prev
    Next
    INDEX
    Explanations

    sectionphasesteppartvolumegroupexperimentchapter

    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_34/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
     nélk
    -1.20
    楽しむ
    -1.13
    衪
    -1.11
     dekoratif
    -1.11
     asisten
    -1.08
    ハロウィン
    -1.08
    🌀
    -1.07
     bensin
    -1.05
    
    -1.04
    Чтоб
    -1.03
    POSITIVE LOGITS
    第
    1.69
     Chapter
    1.38
     Section
    1.16
     Step
    1.16
     both
    1.05
     Theorem
    1.02
     Figure
    0.98
     Phase
    0.97
     Episode
    0.91
     Part
    0.88
    Activations Density 0.105%

    No Known Activations