© 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. 110584
    Prev
    Next
    INDEX
    Explanations

    Huskies, JBL, EDD, XHTML, ATI

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

    brand names and proper nouns, particularly sports team names (especially "Huskies") and product/company names (like "JBL").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    .,
    -3.00
    }_{
    -2.97
    ↵
    -2.69
    ";
    -2.63
    It
    -2.58
    ३
    -2.50
    <em>
    -2.50
    ();
    -2.45
    </sup>
    -2.38
    },
    -2.34
    POSITIVE LOGITS
     hinder
    2.53
    ÖN
    2.47
    
    2.44
     ولی
    2.44
    跄
    2.41
    樒
    2.38
    𝓑
    2.36
    靫
    2.36
     dirait
    2.31
    sivamente
    2.28
    Activations Density 0.009%

    No Known Activations