© 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. 54523
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions before parentheses

    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
     in
    -2.17
    だが
    -1.98
     
    -1.96
    <bos>
    -1.95
     spesifik
    -1.92
     from
    -1.86
     возможность
    -1.84
    だけど
    -1.83
    を
    -1.80
     (
    -1.77
    POSITIVE LOGITS
    卧槽
    2.44
    嵛
    2.39
    
    2.38
    場所で
    2.34
    也會
    2.34
     produkcji
    2.31
     ร์
    2.31
    䊊
    2.25
    際には
    2.23
     dobr
    2.22
    Activations Density 0.007%

    No Known Activations