© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98469
    Prev
    Next
    INDEX
    Explanations

    UK organisations, Herb Reed, workshops seek

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

    The neuron flags words that serve as news‐style metadata—time markers, place names, acronyms and event keywords (e.g. “week,” “UK,” “strike,” “Old,” “City,” “Hebron,” “blocks”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ↵
    -1.26
     sogenannten
    -1.04
     so
    -1.03
     because
    -1.03
    ߋ
    -1.02
    nolo
    -1.02
    Explicit
    -0.98
     our
    -0.98
    </tr>
    -0.98
     поэтому
    -0.96
    POSITIVE LOGITS
    RouterModule
    1.25
    BrowserModule
    1.06
    ituation
    1.04
    isim
    1.02
    aried
    0.98
     fuq
    0.98
    }');
    0.98
     again
    0.98
    aturas
    0.98
    ھے
    0.98
    Activations Density 0.000%

    No Known Activations