© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    medical, technical, or biological subjects

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

    technical terms associated with various types of vehicles, machines, and medical devices.

    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
    さまでした
    -1.30
     después
    -1.16
    ismatic
    -1.15
     fueran
    -1.15
     siempre
    -1.15
    様でした
    -1.11
    )});
    -1.10
    )+\
    -1.09
     occhi
    -1.09
    ,:);
    -1.09
    POSITIVE LOGITS
    like
    1.27
     like
    1.25
     MECHANICAL
    1.16
     firft
    1.08
    摳
    1.06
     BARBARA
    1.05
    冚
    1.05
    sätzlich
    1.05
    without
    1.03
     Âge
    1.02
    Activations Density 0.580%

    No Known Activations