© 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. 127629
    Prev
    Next
    INDEX
    Explanations

    necklace, plasmid, Q

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

    This neuron activates for jewelry items (like necklaces) and molecular biology terms (like plasmids).

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

    the word “necklace” (including its plural form) in the text.

    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
    {
    -3.47
    The
    -3.06
    *
    -2.70
     RequestMethod
    -2.55
    艄
    -2.52
     dava
    -2.45
    ā
    -2.31
    This
    -2.25
     riva
    -2.23
    ."
    -2.20
    POSITIVE LOGITS
    ↵
    2.73
     esperando
    2.61
    <bos>
    2.48
     solicitar
    2.36
    明显的
    2.36
    鴞
    2.34
     
    2.34
     poderos
    2.25
     descub
    2.17
     queridos
    2.17
    Activations Density 0.002%

    No Known Activations