© 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. 64879
    Prev
    Next
    INDEX
    Explanations

    medical terms and demographics

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

    scientific terminology related to chemical compounds, body parts, and laboratory measurements.

    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
    ).
    -1.27
    </tr>
    -1.23
     this
    -1.13
    。
    -1.08
     --
    -1.07
    }$.
    -1.07
    .”
    -1.06
     their
    -1.06
    corrhi
    -1.04
    の基本
    -0.99
    POSITIVE LOGITS
    rrrrr
    1.11
    setters
    1.04
    Azul
    1.04
    rrrrrr
    1.02
    rrrrrrrr
    1.01
     "*",
    1.01
    heds
    1.01
    !!,
    1.00
    oooooo
    1.00
    eeeee
    0.99
    Activations Density 0.115%

    No Known Activations