© 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. 22-GEMMASCOPE-RES-131K
    7. 26149
    Prev
    Next
    INDEX
    Explanations

    biological pathways and citations

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

    technical text elements like measurements, sections, or properties in scientific and technical documents.

    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_22/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
     can
    -1.44
     when
    -1.44
     for
    -1.33
     at
    -1.30
    Two
    -1.28
     When
    -1.27
    There
    -1.24
     could
    -1.23
     There
    -1.23
     While
    -1.22
    POSITIVE LOGITS
     specif
    1.23
     miniaturka
    1.19
     dát
    1.18
     rése
    1.17
     kapture
    1.17
     trám
    1.16
     gewi
    1.16
     ་
    1.11
     zoude
    1.11
    uccess
    1.10
    Activations Density 0.041%

    No Known Activations