© 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. 22-GEMMASCOPE-RES-131K
    7. 68766
    Prev
    Next
    INDEX
    Explanations

    alternatives or choices

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

    This neuron detects words and phrases that introduce or concern numeric quantities or measurements (e.g., “how many,” “days,” “potential,” “impact”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     TELEPHONE
    -1.12
     GRATU
    -1.10
     بسیاری
    -1.06
    tetur
    -1.05
    <td>
    -1.05
     poil
    -1.04
     honn
    -1.02
    зраст
    -1.02
     againſt
    -1.00
    
    -0.98
    POSITIVE LOGITS
     or
    2.13
     или
    1.20
     maybe
    1.16
     what
    1.12
    或者
    1.07
    營業
    1.06
     before
    1.02
     different
    1.02
    或
    1.01
     when
    0.99
    Activations Density 0.012%

    No Known Activations