© 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. 22-GEMMASCOPE-RES-131K
    7. 38798
    Prev
    Next
    INDEX
    Explanations

    onset, speed, or relief

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

    The neuron detects expressions of time spans or durations (e.g. numeric ranges with time units and related temporal markers).

    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
     Bewußt
    -1.04
     recentemente
    -1.03
    etzung
    -0.98
     curent
    -0.93
    available
    -0.93
     воздух
    -0.93
     unseres
    -0.91
    Caracteristici
    -0.91
    を見つけ
    -0.91
     оказалось
    -0.91
    POSITIVE LOGITS
     you
    1.49
     after
    1.44
     your
    1.40
     results
    1.34
     effect
    1.30
     immediate
    1.27
     effects
    1.27
     noticeable
    1.26
     immediately
    1.26
     empezar
    1.24
    Activations Density 0.034%

    No Known Activations