© 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. 65598
    Prev
    Next
    INDEX
    Explanations

    lovers, fans, amateurs

    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
    怎么回事
    -2.22
    
    -1.91
     wygod
    -1.91
     propietarios
    -1.88
    ⸂
    -1.88
    裢
    -1.86
    ﮦ
    -1.85
    を活用
    -1.84
    の魅力
    -1.83
    eket
    -1.83
    POSITIVE LOGITS
    <i>
    3.33
    </td>
    2.47
    <b>
    2.20
    -
    2.05
    they
    1.91
    <sup>
    1.88
    3
    1.88
    1
    1.83
    d
    1.83
     of
    1.83
    Activations Density 0.006%

    No Known Activations