Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110217
    Prev
    Next
    INDEX
    Explanations

    mouth and lips

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

    proximity of objects to a person's mouth or oral area.

    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
     Nh
    -0.71
     psz
    -0.70
    estruct
    -0.68
    锭
    -0.67
    make
    -0.67
     Helga
    -0.66
     democracies
    -0.65
    イナー
    -0.65
    forms
    -0.64
    𝙘
    -0.64
    POSITIVE LOGITS
     mouth
    5.22
     mouths
    3.75
     Mouth
    3.53
    Mouth
    3.48
    mouth
    3.42
    口
    2.77
     lips
    2.39
     рот
    2.38
    MOUTH
    2.38
     mulut
    2.34
    Activations Density 0.031%

    No Known Activations