© 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. 86596
    Prev
    Next
    INDEX
    Explanations

    districts and provinces

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

    The neuron detects mentions of administrative divisions or place‐level jurisdiction terms (e.g. district, state, region, taluk).

    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
     that
    -2.55
     this
    -2.00
     a
    -1.94
     and
    -1.76
    ina
    -1.71
     just
    -1.59
     folosi
    -1.53
     also
    -1.48
     on
    -1.45
     here
    -1.45
    POSITIVE LOGITS
    ↵↵
    1.74
        
    1.71
     „
    1.56
    Nội
    1.52
            
    1.38
     некоторых
    1.38
     („
    1.36
    你有
    1.34
    惊艳
    1.34
     этих
    1.33
    Activations Density 0.057%

    No Known Activations