© 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. 98520
    Prev
    Next
    INDEX
    Explanations

    question markers

    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
    inginan
    -1.20
    ţele
    -1.15
    konos
    -1.13
     laboratoire
    -1.11
    lasyon
    -1.08
    !\
    -1.07
    thodoxy
    -1.06
    section
    -1.05
     and
    -1.05
     actrice
    -1.05
    POSITIVE LOGITS
     you
    1.62
     they
    1.34
    もあって
    1.30
    いただける
    1.26
    思います
    1.25
     gjelder
    1.23
    いただけます
    1.16
    もありますが
    1.16
    ニョ
    1.14
    だと思います
    1.12
    Activations Density 0.003%

    No Known Activations