© 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. 105213
    Prev
    Next
    INDEX
    Explanations

    contractions ending in n't

    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
     ensures
    -4.03
     enormous
    -3.69
     makes
    -3.64
     takes
    -3.59
     creates
    -3.58
     does
    -3.58
     has
    -3.58
     impeccable
    -3.55
     gets
    -3.53
     tells
    -3.45
    POSITIVE LOGITS
    trying
    3.25
    Doesn
    3.05
    does
    2.95
    傒
    2.91
    without
    2.88
    Didn
    2.80
    椟
    2.77
    Seems
    2.73
     EIGHT
    2.69
     HUND
    2.69
    Activations Density 0.003%

    No Known Activations