© 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. 10-GEMMASCOPE-RES-131K
    7. 66374
    Prev
    Next
    INDEX
    Explanations

    citations with years or numbers

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

    The neuron activates on tokens representing floating‐point numeric values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     himself
    -1.34
    𝐘
    -1.23
    ال
    -1.20
    ஜ
    -1.20
     also
    -1.17
     baloncesto
    -1.14
     boxeo
    -1.13
     instead
    -1.11
    ignée
    -1.09
     herself
    -1.08
    POSITIVE LOGITS
     themselves
    1.82
     nhau
    1.41
     själva
    1.37
    PvB
    1.25
    はもう
    1.23
     it
    1.22
    though
    1.21
     encantó
    1.20
    してくれた
    1.20
    asteroido
    1.19
    Activations Density 0.028%

    No Known Activations