© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78681
    Prev
    Next
    INDEX
    Explanations

    unpleasant smells or odors

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

    words and phrases related to unpleasant smells and 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_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
     clatter
    -0.81
    音声
    -0.80
    MENT
    -0.80
    摩
    -0.77
    ナイ
    -0.77
     sound
    -0.76
    Sc
    -0.75
     epile
    -0.75
    Subscribed
    -0.75
     sounds
    -0.75
    POSITIVE LOGITS
     rotten
    1.52
     foul
    1.35
     unpleasant
    1.34
    rotten
    1.14
     rotting
    1.09
    Rotten
    1.08
     bad
    1.05
     offensive
    1.05
     sulfur
    1.03
     stink
    1.02
    Activations Density 0.010%

    No Known Activations