© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific words

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

    The neuron fires on numeric tokens, i.e. it detects numbers 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
    Pele
    -0.67
     descargar
    -0.67
     แท
    -0.67
    Jegyzetek
    -0.67
     Etienne
    -0.66
     diseñados
    -0.66
    gänge
    -0.66
     decrypted
    -0.66
    ⓓ
    -0.66
     leg
    -0.65
    POSITIVE LOGITS
     lamp
    1.14
     Chord
    0.96
     chord
    0.95
     tunic
    0.94
     Lamp
    0.94
    Lamp
    0.91
    WriteBarrier
    0.87
    Chord
    0.86
     noto
    0.79
     Lance
    0.78
    Activations Density 0.043%

    No Known Activations