© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47711
    Prev
    Next
    INDEX
    Explanations

    polyurethane, Cushing, bristles, bushings

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

    names of small mechanical parts or components like bushings, bristles, and grout.

    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
    翃
    -2.36
    嘸
    -2.33
     駅前
    -2.25
     ,‬
    -2.23
    餮
    -2.20
     humeur
    -2.20
    窳
    -2.20
    躥
    -2.19
    釹
    -2.13
    🧌
    -2.11
    POSITIVE LOGITS
    嫱
    2.70
    </b>
    2.20
     \"
    2.19
    𝘵
    2.09
     &
    2.08
    geſ
    2.06
    ll
    2.03
    乆
    2.02
     \_
    1.92
    靫
    1.90
    Activations Density 0.007%

    No Known Activations