© 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. 30888
    Prev
    Next
    INDEX
    Explanations

    inner ear

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

    mentions of ears or hearing-related terms.

    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
    istro
    -0.78
     MOB
    -0.74
     onView
    -0.73
    cytic
    -0.71
     ته
    -0.71
     мето
    -0.71
    看得
    -0.70
    見到
    -0.69
     sehen
    -0.69
    lights
    -0.69
    POSITIVE LOGITS
     ears
    6.06
     ear
    5.19
     Ears
    4.13
    耳
    4.06
    ears
    3.47
     Ear
    3.23
    耳朵
    3.19
    Ear
    3.17
    ear
    3.02
     耳
    2.88
    Activations Density 0.037%

    No Known Activations