© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27880
    Prev
    Next
    INDEX
    Explanations

    esophageal and escherichia

    np_acts-logits-general · gemini-2.5-flash-lite

    references to ECMAScript or ES (JavaScript specification) followed by version numbers or technical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    </td>
    -3.11
    犼
    -2.94
    摟
    -2.72
    豋
    -2.56
    
    -2.56
     ミニ
    -2.55
    </b>
    -2.53
     唯美
    -2.50
     ジップ
    -2.48
    不断的
    -2.47
    POSITIVE LOGITS
    {
    2.55
     This
    2.44
     There
    2.38
    *
    2.38
    鷺
    2.36
    靄
    2.17
     erotic
    2.17
    咔嚓
    2.16
    東南
    2.16
     hasn
    2.11
    Activations Density 0.043%

    No Known Activations