© 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. 39492
    Prev
    Next
    INDEX
    Explanations

    wanted or help wanted

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

    The neuron fires on mentions of “wanted” (and its variants like fugitive/fugitives) in contexts such as criminal alerts, job ads, or help-wanted notices.

    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
    鱨
    -2.33
    儅
    -2.28
    咵
    -2.14
    馓
    -2.11
     ModelAndView
    -2.06
    acterísticas
    -1.98
    艄
    -1.98
    蟶
    -1.97
     prega
    -1.96
    臯
    -1.95
    POSITIVE LOGITS
    ↵↵
    2.94
     These
    2.86
     Those
    2.63
     in
    2.58
     However
    2.53
     Since
    2.44
     From
    2.44
     That
    2.34
    </sup>
    2.34
     Essentially
    2.28
    Activations Density 0.006%

    No Known Activations