© 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. 45327
    Prev
    Next
    INDEX
    Explanations

    psychosocial functioning and immunotherapy treatment

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

    news sources and technical/professional terminology in scientific and medical 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_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
    轱
    -2.39
    嬗
    -2.02
    unpublished
    -2.00
    十分钟
    -1.98
    ⽤
    -1.95
    </i>
    -1.94
     gerçek
    -1.91
    自身が
    -1.88
    </h3>
    -1.87
    摇了
    -1.84
    POSITIVE LOGITS
    琑
    2.36
    、
    2.34
    at
    2.30
    for
    2.28
    栳
    2.25
     BRARY
    2.19
    on
    2.08
    “
    2.05
    では
    2.03
    x
    2.03
    Activations Density 0.020%

    No Known Activations