© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129593
    Prev
    Next
    INDEX
    Explanations

    septum, partition, diaphragm

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

    anatomical terms related to septum structures in medical and scientific texts.

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

    The neuron detects occurrences of “sept” (as in septum, septal, etc.), i.e. mentions of anatomical septal structures.

    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
    
    -1.41
    Conversions
    -1.39
    larına
    -1.34
     tisíc
    -1.32
    thun
    -1.32
    städ
    -1.31
     nového
    -1.30
    Translations
    -1.30
    Voter
    -1.30
    passen
    -1.29
    POSITIVE LOGITS
    .’
    1.85
    これらの
    1.60
    </u>
    1.60
    }:
    1.57
    ).
    1.56
     by
    1.49
    )});
    1.46
     been
    1.45
     usare
    1.45
    .)
    1.44
    Activations Density 0.059%

    No Known Activations