© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9444
    Prev
    Next
    INDEX
    Explanations

    preparatory, archival, saline

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

    The neuron activates on adjectives that specify types or categories—especially “preparatory” and “archival” modifiers.

    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
     …..
    -3.05
    \
    -2.97
     …
    -2.66
     ……
    -2.50
    -
    -2.47
     
    -2.45
     ‘
    -2.44
     magnific
    -2.41
     leſs
    -2.39
    ve
    -2.33
    POSITIVE LOGITS
    </sub>
    2.97
     longstanding
    2.64
    鮟
    2.36
    巿
    2.33
     ricordare
    2.31
     unrelenting
    2.31
     groundbreaking
    2.28
     esigen
    2.27
    作品の
    2.25
    ית
    2.22
    Activations Density 0.004%

    No Known Activations