© 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. 34-GEMMASCOPE-RES-131K
    7. 99044
    Prev
    Next
    INDEX
    Explanations

    gel variations in compounds

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

    words starting with "Gel" such as Gelatin, Gelato, and Gel (including when part of product names).

    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_34/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
    瑭
    -0.89
    le
    -0.85
    ткий
    -0.81
    回復
    -0.81
    ement
    -0.78
     چیز
    -0.76
    termilk
    -0.76
    ർ
    -0.75
    त्य
    -0.75
    几个月
    -0.73
    POSITIVE LOGITS
     Gel
    0.88
     einstellen
    0.85
     verdienen
    0.81
    etermined
    0.79
    Gel
    0.76
     Atletico
    0.76
     hippocampal
    0.76
     retardation
    0.75
    ateria
    0.73
    INAS
    0.73
    Activations Density 0.026%

    No Known Activations