© 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. 28609
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    
    -1.91
    哢
    -1.89
    ⬮
    -1.84
    ༐
    -1.84
    蒾
    -1.81
     этих
    -1.78
    pulseira
    -1.78
    </h2>
    -1.78
     quizás
    -1.76
    全世界
    -1.72
    POSITIVE LOGITS
    }
    2.58
    一个月
    1.96
    และ
    1.96
    a
    1.89
    ”
    1.87
    er
    1.77
     —
    1.76
    </u>
    1.75
    In
    1.72
    the
    1.71
    Activations Density 0.023%

    No Known Activations