© 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. 10-GEMMASCOPE-RES-131K
    7. 60983
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    The neuron chiefly responds to numeric expressions and quantitative details (e.g. distances, durations, measurements, counts).

    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
     diámetro
    -1.79
     ส์
    -1.73
     ſever
    -1.72
     espesor
    -1.70
    ervant
    -1.65
    撂
    -1.59
     secador
    -1.58
     Katowice
    -1.58
     jezt
    -1.58
     ligera
    -1.58
    POSITIVE LOGITS
    .
    2.03
     two
    1.99
     in
    1.86
    —
    1.84
    Two
    1.80
     we
    1.77
     four
    1.77
     of
    1.76
     other
    1.75
     one
    1.73
    Activations Density 0.004%

    No Known Activations