© 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. 22-GEMMASCOPE-RES-131K
    7. 528
    Prev
    Next
    INDEX
    Explanations

    hygiene and conditions

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

    words and phrases related to unpleasant or unhygienic conditions.

    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_22/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
    的眼睛
    -1.08
    drawSprites
    -1.07
     espirituales
    -1.06
     Milch
    -1.05
    クエ
    -1.02
    花了
    -0.99
    となると
    -0.99
     miseries
    -0.98
    ULATE
    -0.98
     sio
    -0.98
    POSITIVE LOGITS
    ಆ
    1.11
     Benutz
    1.09
    cocina
    1.06
     Kesehatan
    1.06
    ಇ
    1.04
     Inhalten
    1.02
    پاسخ
    1.02
     cleanliness
    1.02
    junto
    1.00
    демо
    0.99
    Activations Density 0.053%

    No Known Activations