© 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. 34-GEMMASCOPE-RES-131K
    7. 99782
    Prev
    Next
    INDEX
    Explanations

    US cities and states

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

    The neuron activates on numeric tokens and data (years, counts, route numbers, population figures, etc.).

    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
     Rückkehr
    -0.72
    यर
    -0.72
     intracranial
    -0.71
    GrantedAuthority
    -0.71
    rator
    -0.70
     amphibians
    -0.70
    CHAMP
    -0.69
    Anil
    -0.67
    AMP
    -0.66
     Temporal
    -0.66
    POSITIVE LOGITS
     Shenandoah
    1.55
    Shen
    1.24
     Potomac
    0.98
     shen
    0.87
     Berkeley
    0.82
    Berkeley
    0.81
     Hager
    0.80
     Baltimore
    0.78
     Winchester
    0.77
     VIRGINIA
    0.76
    Activations Density 0.017%

    No Known Activations