© 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. 116668
    Prev
    Next
    INDEX
    Explanations

    filtering and selection

    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
    逛
    -0.80
     vamp
    -0.80
    Klub
    -0.79
    nexpected
    -0.79
    靭
    -0.78
    lagte
    -0.77
    himp
    -0.77
    ój
    -0.75
    interopRequire
    -0.74
    โร
    -0.74
    POSITIVE LOGITS
     filter
    3.72
    filter
    3.42
     Filter
    2.66
    Filter
    2.53
     filtering
    2.50
     filters
    2.44
     FILTER
    2.42
    FILTER
    2.30
     filtered
    2.13
     Filtering
    2.13
    Activations Density 0.027%

    No Known Activations