© 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. 22-GEMMASCOPE-RES-131K
    7. 35090
    Prev
    Next
    INDEX
    Explanations

    chapter followed by number or roman numeral

    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
    their
    -1.09
    Их
    -1.08
    他們的
    -1.01
     à
    -1.00
    ERRY
    -1.00
     fraî
    -0.99
     categorize
    -0.99
    though
    -0.99
    unning
    -0.97
    操作系统
    -0.97
    POSITIVE LOGITS
     chapter
    1.27
     chapters
    1.16
     of
    1.10
     Lleva
    1.09
     bölüm
    1.05
    borgen
    1.05
    chapter
    1.05
    MultipartFile
    1.05
     уже
    1.04
     burgeoning
    1.04
    Activations Density 0.008%

    No Known Activations