© 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. 34-GEMMASCOPE-RES-131K
    7. 115951
    Prev
    Next
    INDEX
    Explanations

    full descriptions

    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_34/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
    subsec
    -0.91
     empiezan
    -0.88
     largely
    -0.86
     padrão
    -0.84
    standen
    -0.83
     fechas
    -0.82
     Ль
    -0.82
     overuse
    -0.82
    zdjęcie
    -0.81
    脍
    -0.80
    POSITIVE LOGITS
     including
    1.52
     full
    1.38
    full
    1.33
     включая
    1.32
    including
    1.07
     Full
    1.06
    fledged
    1.05
    Full
    1.05
    フル
    1.04
     coverage
    1.01
    Activations Density 0.067%

    No Known Activations