© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39610
    Prev
    Next
    INDEX
    Explanations

    places, entities, or time periods

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

    The neuron activates on numeral‐containing tokens—i.e. numbers, numeric measurements, or version identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     or
    -1.69
     through
    -1.44
     including
    -1.43
     from
    -1.39
     during
    -1.39
     even
    -1.26
     their
    -1.26
     such
    -1.25
     both
    -1.18
     using
    -1.16
    POSITIVE LOGITS
     bateaux
    1.20
     boucles
    1.19
     roues
    1.13
    Means
    1.09
     carrés
    1.08
     eikä
    1.08
     tirs
    1.06
     disques
    1.06
    而不是
    1.05
     bandes
    1.05
    Activations Density 0.030%

    No Known Activations