© 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. 59386
    Prev
    Next
    INDEX
    Explanations

    biological linings and structures

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

    terms related to biological tissues, particularly "mucosa" and anatomical structures like "fort".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly responds to capitalized multi-letter terms—especially acronyms or proper-noun tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ⢓
    -3.00
    酲
    -2.67
    ان
    -2.67
    牁
    -2.38
    蛱
    -2.38
    辚
    -2.36
    Ꮨ
    -2.36
    伃
    -2.33
    錒
    -2.30
    迩
    -2.25
    POSITIVE LOGITS
     $
    3.05
     '
    2.92
     -
    2.88
    —
    2.83
    \
    2.73
    ,"
    2.67
    "
    2.67
     weiße
    2.61
     grüne
    2.58
     If
    2.47
    Activations Density 0.004%

    No Known Activations