© 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. 34-GEMMASCOPE-RES-131K
    7. 64058
    Prev
    Next
    INDEX
    Explanations

    city manager, 3-point shots

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

    The main thing this neuron does is identify specific place names (geographic locations or venues).

    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
    hemd
    -0.80
    spu
    -0.75
     IService
    -0.73
     Kurse
    -0.72
    Cita
    -0.72
     Haft
    -0.71
    dicion
    -0.69
     HATE
    -0.68
     aufs
    -0.66
    Elvis
    -0.66
    POSITIVE LOGITS
     Esper
    0.88
    timiento
    0.82
    izaje
    0.81
     Randolph
    0.77
    انو
    0.77
    มาะ
    0.77
    ̲
    0.75
    ğlık
    0.75
     Wyndham
    0.74
    حت
    0.74
    Activations Density 0.012%

    No Known Activations