© 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. 95744
    Prev
    Next
    INDEX
    Explanations

    code closing punctuation

    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
    (
    -1.20
    laboration
    -1.16
    kram
    -1.08
    tapis
    -1.07
    paru
    -1.06
     naše
    -1.05
     and
    -1.03
     of
    -1.02
    dji
    -1.02
     berbagai
    -1.01
    POSITIVE LOGITS
    Халы
    1.16
    每個
    1.12
    ");
    1.11
    !!!!!
    1.09
    !!!!
    1.09
    !!!
    1.09
    Каждый
    1.07
     stata
    1.06
    両方
    1.06
     now
    1.05
    Activations Density 0.009%

    No Known Activations