© 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. 113309
    Prev
    Next
    INDEX
    Explanations

    autism spectrum disorders

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

    terms related to autism spectrum disorders and organizational names ending with "sters" or "aro".

    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
    そろそろ
    -1.52
     of
    -1.39
    ным
    -1.35
     and
    -1.34
     начале
    -1.33
    ……
    -1.30
    М
    -1.29
    Zunanje
    -1.27
    ер
    -1.26
    кой
    -1.26
    POSITIVE LOGITS
     Beberapa
    1.57
     mógł
    1.56
    させていただきました
    1.54
    rozco
    1.53
    珎
    1.53
     revisión
    1.52
     régiment
    1.51
    幾天
    1.51
     komment
    1.51
     حتی
    1.51
    Activations Density 0.096%

    No Known Activations