© 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. 48510
    Prev
    Next
    INDEX
    Explanations

    writing in a context or location

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

    The neuron activates on numerical tokens (e.g., years, counts, or other 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_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
     which
    -1.56
     they
    -1.38
     οποίο
    -1.30
     their
    -1.25
     its
    -1.20
     it
    -1.18
     gets
    -1.10
     οποία
    -1.07
     including
    -1.00
     경우
    -1.00
    POSITIVE LOGITS
     accordance
    1.36
    řejmě
    1.28
     klasa
    1.27
     collaboration
    1.24
     conjunction
    1.23
     by
    1.21
     okazji
    1.21
     bezw
    1.20
     dezelfde
    1.13
     auspices
    1.13
    Activations Density 0.174%

    No Known Activations