© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47740
    Prev
    Next
    INDEX
    Explanations

    effective immediately / with effect from

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

    The neuron fires on time-of-effect phrases, especially “immediate(ly)” or “effective” indicating something takes effect at once.

    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
    Occurred
    -1.45
     two
    -1.43
    łem
    -1.34
     extré
    -1.27
    ’)
    -1.27
     still
    -1.27
    nem
    -1.25
    ถ้า
    -1.25
     tomba
    -1.24
    鱟
    -1.24
    POSITIVE LOGITS
    7
    1.64
    5
    1.63
    6
    1.52
     fiyatları
    1.49
    8
    1.48
     Nachfrage
    1.47
     Roughly
    1.39
     aktuellen
    1.38
    各式
    1.38
    或者
    1.37
    Activations Density 0.010%

    No Known Activations