© 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. 72923
    Prev
    Next
    INDEX
    Explanations

    Dual followed by reporter

    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
     and
    -2.31
    戗
    -1.97
    ྥ
    -1.84
    蛩
    -1.84
    <bos>
    -1.78
    錵
    -1.75
    this
    -1.72
    lampada
    -1.71
    owym
    -1.70
     badkamer
    -1.67
    POSITIVE LOGITS
     it
    2.58
    </strong>
    2.23
    越是
    1.94
     所以
    1.92
     Their
    1.80
     Also
    1.78
    樒
    1.77
     podem
    1.76
     Therefore
    1.74
     cirka
    1.72
    Activations Density 0.000%

    No Known Activations