© 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. 73370
    Prev
    Next
    INDEX
    Explanations

    bone properties, conditions, and treatments

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

    references to bone and skeletal structures in medical and scientific contexts.

    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
    t
    -2.55
    .
    -2.33
    >
    -2.19
    d
    -2.17
    蹀
    -2.13
    !
    -2.03
    of
    -2.03
    ats
    -1.97
    猡
    -1.97
    )
    -1.93
    POSITIVE LOGITS
    ？』
    2.36
     umumnya
    2.13
     of
    2.09
    場合
    2.08
     incluindo
    1.98
     biasanya
    1.96
     December
    1.95
    燹
    1.94
     trough
    1.93
     awalnya
    1.92
    Activations Density 0.051%

    No Known Activations