© 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. 22211
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

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

    technical terms, particularly in scientific or computing contexts.

    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
    Caratteristiche
    -1.45
     jadx
    -1.38
    ciamento
    -1.37
     zumal
    -1.37
     wäre
    -1.32
    }
    -1.31
    umento
    -1.29
     lụ
    -1.28
     a
    -1.27
     insistence
    -1.27
    POSITIVE LOGITS
     niekoľ
    1.44
    "$_
    1.27
    ,
    1.26
     medlemmer
    1.26
     蟹
    1.22
    わが
    1.22
     Familienname
    1.22
     hemel
    1.21
    career
    1.20
     vänner
    1.20
    Activations Density 0.116%

    No Known Activations