© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43997
    Prev
    Next
    INDEX
    Explanations

    Kulda, Kuldip, Kulbin, alkaloids, Shelley, Lucie, Cáceres, xsi

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

    names with "Kul" in them and chemical or biological terms like "alkaloids".

    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_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
    </h3>
    -3.66
    la
    -2.98
    as
    -2.89
    }=\
    -2.72
    其妙
    -2.56
    」「
    -2.55
    ázaro
    -2.50
    瀲
    -2.48
    </i>
    -2.47
    )))
    -2.47
    POSITIVE LOGITS
     
    3.22
    が欲しい
    2.52
    を買う
    2.48
    を選び
    2.45
    很是
    2.44
    家乡
    2.44
     brinquedos
    2.42
     besonder
    2.34
     малень
    2.31
     schönen
    2.30
    Activations Density 0.068%

    No Known Activations