© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27691
    Prev
    Next
    INDEX
    Explanations

    body parts and senses

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

    body parts, particularly in contexts describing physical sensations or experiences.

    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
     you
    -1.88
     I
    -1.46
     it
    -1.45
     its
    -1.42
     pamoja
    -1.30
    為に
    -1.28
     your
    -1.24
    -1.24
    あー
    -1.23
     indivíduos
    -1.19
    POSITIVE LOGITS
    一品
    1.37
     conster
    1.34
    Răsp
    1.32
     pousada
    1.27
     during
    1.26
     trajet
    1.26
    Aç
    1.24
    Väl
    1.24
     parar
    1.23
    دانلود
    1.23
    Activations Density 0.024%

    No Known Activations