© 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. 35542
    Prev
    Next
    INDEX
    Explanations

    code syntax and declarations

    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
     bluz
    -1.32
     豬
    -1.23
    layın
    -1.23
     plakat
    -1.22
     trener
    -1.18
    spania
    -1.17
    Szer
    -1.15
    Več
    -1.15
    США
    -1.14
     pistolet
    -1.14
    POSITIVE LOGITS
    pro
    1.16
    ^
    1.13
    p
    1.13
    a
    1.09
     aynı
    1.08
     are
    1.06
    J
    1.05
    更加
    1.05
    id
    1.04
     idea
    1.03
    Activations Density 0.176%

    No Known Activations