© 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. 44377
    Prev
    Next
    INDEX
    Explanations

    Historic Places, Embase, polyacrylamide

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

    academic database and research registry names like "Embase", "Historic Register", and "PubMed".

    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
    -1.57
     the
    -1.57
     is
    -1.48
     होता
    -1.42
     encontrarás
    -1.34
     verschill
    -1.23
    了很多
    -1.23
     sentada
    -1.20
     añadió
    -1.19
     into
    -1.17
    POSITIVE LOGITS
     människor
    1.54
    </h5>
    1.46
     jeho
    1.40
     ABBREVIATIONS
    1.35
    </em>
    1.30
     varandra
    1.25
    irmanship
    1.21
    珧
    1.21
     sportivo
    1.20
    
    1.20
    Activations Density 0.503%

    No Known Activations