© 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. 60729
    Prev
    Next
    INDEX
    Explanations

    past/non-past verb tense

    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
     pecans
    -0.82
     where
    -0.81
     **/
    -0.79
     of
    -0.79
     mossy
    -0.78
     how
    -0.76
    ”、“
    -0.74
     with
    -0.73
     pecan
    -0.72
     while
    -0.72
    POSITIVE LOGITS
    ually
    0.88
     ворот
    0.84
    atics
    0.82
     simplu
    0.82
     áng
    0.81
    Namespaces
    0.81
     nô
    0.81
    Plain
    0.80
     portanto
    0.80
    एं
    0.79
    Activations Density 0.008%

    No Known Activations