© 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. 64704
    Prev
    Next
    INDEX
    Explanations

    mountains and geographic locations

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

    The neuron detects numeric tokens—i.e. numbers and other digit-based expressions in the text.

    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
    žo
    -0.75
     торже
    -0.75
    ieds
    -0.74
     concentrates
    -0.71
     функции
    -0.71
    ťa
    -0.69
     fundada
    -0.69
    Bridge
    -0.69
    arbol
    -0.69
     classes
    -0.68
    POSITIVE LOGITS
     summits
    0.99
     summit
    0.96
     ridges
    0.86
    ragamo
    0.81
     carrière
    0.81
    transmitter
    0.80
     transmitter
    0.76
     Backend
    0.74
     escarp
    0.74
    خاذ
    0.73
    Activations Density 0.059%

    No Known Activations