© 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. 98870
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

    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
    aría
    -0.91
    ould
    -0.86
     %,
    -0.83
    甀
    -0.82
    泮
    -0.82
     '');
    -0.82
    給我
    -0.79
    ría
    -0.79
     Hunde
    -0.78
    Erreferent
    -0.78
    POSITIVE LOGITS
     advise
    1.33
     will
    1.16
     heard
    1.01
     advice
    0.95
    ECK
    0.90
     wonder
    0.86
     ask
    0.85
     originally
    0.84
     want
    0.81
    趣
    0.80
    Activations Density 0.004%

    No Known Activations