© 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. 127448
    Prev
    Next
    INDEX
    Explanations

    am, can, has, is, would

    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
    ”
    -2.19
    :
    -2.08
     from
    -1.95
     —
    -1.91
    0
    -1.88
    ."
    -1.88
    "
    -1.88
     [
    -1.88
    $
    -1.85
    ”.
    -1.83
    POSITIVE LOGITS
     however
    1.95
     όμως
    1.88
    Namun
    1.88
     inoltre
    1.84
    Kemudian
    1.80
    さてさて
    1.77
    鉏
    1.77
    ῞
    1.77
    もありますが
    1.71
     them
    1.70
    Activations Density 0.420%

    No Known Activations