© 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. 34-GEMMASCOPE-RES-131K
    7. 103312
    Prev
    Next
    INDEX
    Explanations

    quantities and units

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

    The neuron is keyed to temporal expressions—especially date/duration language (e.g. “on” dates, “to” ranges, numeric day/year tokens).

    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
    alder
    -0.85
    paya
    -0.81
    ప్ర
    -0.80
    ∐
    -0.80
    쿼
    -0.79
    –
    -0.77
    സി
    -0.74
    teca
    -0.74
    رخ
    -0.73
    Spire
    -0.73
    POSITIVE LOGITS
    OPCODE
    0.75
    um
    0.72
    verso
    0.68
    ramientas
    0.68
     Pass
    0.68
    type
    0.67
    があるので
    0.66
    ICTION
    0.65
    ocu
    0.65
    ower
    0.64
    Activations Density 0.011%

    No Known Activations