© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 548
    Prev
    Next
    INDEX
    Explanations

    programming imports and code structure

    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
    wavering
    -1.43
    anglès
    -1.26
    様な
    -1.25
    Trichloroethane
    -1.25
     ktorá
    -1.25
     verko
    -1.21
    為に
    -1.21
     защото
    -1.19
     rése
    -1.18
    nă
    -1.18
    POSITIVE LOGITS
    その
    1.14
     that
    1.12
     these
    1.10
     Betrachtung
    1.05
     after
    1.05
     those
    1.02
    そのため
    1.02
    結論
    1.01
    a
    1.00
     Hinsicht
    0.99
    Activations Density 0.006%

    No Known Activations