© 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. 10-GEMMASCOPE-RES-131K
    7. 90379
    Prev
    Next
    INDEX
    Explanations

    use choice determine bail

    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_10/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
    Haben
    -1.53
    臯
    -1.51
     brille
    -1.51
     perpé
    -1.49
    もちろん
    -1.48
     mété
    -1.47
     provoque
    -1.44
     maniere
    -1.38
     inaugura
    -1.38
     sujeito
    -1.38
    POSITIVE LOGITS
     and
    2.53
     at
    2.48
     from
    2.17
     in
    2.06
     through
    1.97
     by
    1.95
     as
    1.88
     into
    1.87
     after
    1.73
     all
    1.67
    Activations Density 0.001%

    No Known Activations