© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68438
    Prev
    Next
    INDEX
    Explanations

    vitamins B1, B2, B6, B7, B12

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

    vitamin B references, particularly B1, B2, and other B vitamin designations.

    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
    0
    -1.72
     want
    -1.68
    <
    -1.63
     After
    -1.62
     get
    -1.59
     Get
    -1.57
    </b>
    -1.55
     facilitate
    -1.53
        
    -1.52
     --
    -1.52
    POSITIVE LOGITS
     kilku
    1.79
     ใน
    1.74
     podoba
    1.70
    骉
    1.70
    졍
    1.66
    gewöhn
    1.63
    fassen
    1.63
    鲀
    1.62
    verhält
    1.62
    arbeiten
    1.62
    Activations Density 0.063%

    No Known Activations