© 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. 22-GEMMASCOPE-RES-131K
    7. 128698
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of “facility” or “facilities” (especially when they appear as headings or key section labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    facility characteristics, differing, delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    妧
    -2.53
    檮
    -2.50
     Flasche
    -2.14
    ⦊
    -2.13
     akty
    -2.13
    時候
    -2.13
     Однако
    -2.11
    甶
    -2.11
     wiesz
    -2.06
    ௅
    -2.06
    POSITIVE LOGITS
    ’
    2.70
    <bos>
    2.53
    ”
    2.48
    }
    2.44
    ()
    2.41
    */
    2.39
    this
    2.36
    i
    2.31
    >
    2.25
     questo
    2.16
    Activations Density 0.013%

    No Known Activations