© 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. 107981
    Prev
    Next
    INDEX
    Explanations

    consist of numbers

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

    The main thing this neuron does is detect numeric tokens (digits or multi‐digit 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
    բ
    -0.82
    ob
    -0.78
     At
    -0.74
    badlogic
    -0.69
     Hil
    -0.69
    assertTrue
    -0.69
    Tx
    -0.68
     er
    -0.68
     In
    -0.67
    huis
    -0.66
    POSITIVE LOGITS
     össze
    0.82
    competent
    0.79
     jue
    0.78
    Gets
    0.76
     quelles
    0.76
    MatInputModule
    0.75
     copil
    0.75
     TRAINING
    0.75
    evs
    0.74
    Stephen
    0.74
    Activations Density 0.347%

    No Known Activations