© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12551
    Prev
    Next
    INDEX
    Explanations

    biotin and B vitamins

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

    vitamin names and nutritional compounds, particularly B vitamins, biotin, and other micronutrients.

    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
    嫒
    -1.89
    楦
    -1.72
     verifique
    -1.72
     académico
    -1.67
     evangé
    -1.66
    孥
    -1.65
     turístico
    -1.65
     bené
    -1.61
     encantador
    -1.60
     físico
    -1.59
    POSITIVE LOGITS
     is
    1.91
    する
    1.60
    o
    1.58
    ’
    1.58
    as
    1.53
    in
    1.52
     Damn
    1.45
    ].
    1.45
    9
    1.43
     Rebecca
    1.39
    Activations Density 0.032%

    No Known Activations