© 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. 10-GEMMASCOPE-RES-131K
    7. 99259
    Prev
    Next
    INDEX
    Explanations

    aerosol, droplet, condensed objects

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

    scientific terminology related to particles, aerosols, droplets, and nucleation in atmospheric and physical sciences.

    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
    in
    -1.70
    ou
    -1.62
    k
    -1.57
    er
    -1.55
    al
    -1.54
    ong
    -1.48
    ad
    -1.48
    le
    -1.47
    on
    -1.41
    ment
    -1.40
    POSITIVE LOGITS
     usamos
    1.32
     ويكي
    1.30
    ſing
    1.29
    gemar
    1.29
    empatan
    1.28
    ordum
    1.27
    ælp
    1.26
    Rhône
    1.26
     όταν
    1.26
     consideramos
    1.24
    Activations Density 0.086%

    No Known Activations