© 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. 34-GEMMASCOPE-RES-131K
    7. 56072
    Prev
    Next
    INDEX
    Explanations

    Berkeley, Jefferson, Recreation, West Virginia

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

    The neuron strongly activates on tokens that are part of named entities (especially place names) and numerical/statistical data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    袖
    -0.75
     îl
    -0.71
     vrea
    -0.71
     Bax
    -0.68
    𝕄
    -0.66
    渺
    -0.66
     seguirá
    -0.66
    Uuid
    -0.66
    を整
    -0.66
    時点
    -0.65
    POSITIVE LOGITS
     Berkeley
    1.20
    Berkeley
    1.09
     WV
    0.93
     Potomac
    0.85
    WV
    0.85
     Berk
    0.79
     West
    0.77
     Dirichlet
    0.77
     बु
    0.77
    berkeley
    0.76
    Activations Density 0.021%

    No Known Activations