© 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. 10-GEMMASCOPE-RES-131K
    7. 69673
    Prev
    Next
    INDEX
    Explanations

    smell and sensory perception

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

    the word "smell" followed by contextual information about odors.

    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
    s
    -3.09
    i
    -2.56
    ي
    -2.45
     einige
    -2.41
    怎么能
    -2.39
    Итак
    -2.38
     như
    -2.38
     problemen
    -2.33
    感じ
    -2.31
    ですので
    -2.31
    POSITIVE LOGITS
    .
    2.66
     unſ
    2.42
    weakSelf
    2.36
    ᭡
    2.25
    有不
    2.23
    стойчи
    2.19
     benefiting
    2.14
     санкт
    2.08
    man
    2.06
     enforcing
    2.06
    Activations Density 0.006%

    No Known Activations