© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119631
    Prev
    Next
    INDEX
    Explanations

    odor or odors and associated terms

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

    words related to odor and smell.

    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
    鳎
    -3.41
    ჻
    -3.25
    俛
    -2.92
    齣
    -2.80
    橚
    -2.77
     terzo
    -2.72
     behulp
    -2.69
     της
    -2.69
    鋱
    -2.66
    стреча
    -2.63
    POSITIVE LOGITS
    ↵↵
    3.75
    ↵
    3.47
     
    2.69
    -
    2.58
    ’
    2.44
    ла
    2.31
    ка
    2.25
    1
    2.19
    鴣
    2.13
     étab
    2.11
    Activations Density 0.001%

    No Known Activations