© 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. 22-GEMMASCOPE-RES-131K
    7. 98416
    Prev
    Next
    INDEX
    Explanations

    to action 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_22/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
    astify
    -2.30
    <bos>
    -2.17
    けどね
    -2.05
    巨大的
    -2.03
    家は
    -1.98
    独特的
    -1.91
     optimieren
    -1.81
    中でも
    -1.77
     mempel
    -1.77
    了一个
    -1.73
    POSITIVE LOGITS
     be
    3.00
    ’
    2.20
     μην
    1.96
    大丈夫です
    1.86
     know
    1.86
    They
    1.84
    begin
    1.83
    Their
    1.73
    噥
    1.73
            
    1.70
    Activations Density 0.055%

    No Known Activations