© 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. 4382
    Prev
    Next
    INDEX
    Explanations

    places and services

    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
     Lizenz
    -0.86
    жется
    -0.81
     seperate
    -0.79
    anyang
    -0.79
     haberse
    -0.75
     nacer
    -0.74
    雰囲気
    -0.73
     contain
    -0.73
    iosamente
    -0.72
     benefitted
    -0.72
    POSITIVE LOGITS
    ropractor
    0.97
     VARCHAR
    0.88
    punkt
    0.86
    ITÀ
    0.86
    MetaType
    0.82
    ziesz
    0.82
     autentic
    0.82
     நி
    0.82
     varchar
    0.81
    $$$
    0.81
    Activations Density 0.017%

    No Known Activations