© 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. 47671
    Prev
    Next
    INDEX
    Explanations

    modes of presence and distance

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

    The neuron strongly activates on numeric tokens (digits and numeric quantities) 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
    miş
    -0.82
     Salz
    -0.77
     souha
    -0.72
    ika
    -0.70
    𝗚
    -0.69
    intel
    -0.69
    erg
    -0.69
    bom
    -0.68
    在外
    -0.68
     tritt
    -0.68
    POSITIVE LOGITS
     onsite
    3.09
     presencial
    2.91
     hybrid
    2.16
     face
    2.00
     حض
    1.88
    Hybrid
    1.88
    hybrid
    1.84
     Hybrid
    1.81
     offline
    1.68
     IRL
    1.63
    Activations Density 0.041%

    No Known Activations