© 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. 21456
    Prev
    Next
    INDEX
    Explanations

    acrylamide gel and Akt pathway

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

    references to polyacrylamide gel electrophoresis in scientific texts.

    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
     aquellos
    -1.78
     aquellas
    -1.72
    neurial
    -1.72
    ScopeManager
    -1.63
    CodeAttribute
    -1.58
    jungan
    -1.58
     cubiertos
    -1.53
    (!__
    -1.50
     cuotas
    -1.44
     cercanos
    -1.41
    POSITIVE LOGITS
     for
    2.14
     since
    2.00
     on
    1.64
    ,
    1.48
     a
    1.45
     any
    1.39
    Hilsen
    1.39
    
    1.34
     was
    1.32
    2
    1.30
    Activations Density 0.072%

    No Known Activations