© 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. 115506
    Prev
    Next
    INDEX
    Explanations

    start of an action

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

    The neuron strongly activates on various inflections of the verb “begin” (e.g. began, beginning, begun).

    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
     continuing
    -1.36
    continuing
    -1.32
     acestea
    -1.13
     continuation
    -1.11
     estando
    -1.10
    becoming
    -1.09
     continuer
    -1.05
     beginning
    -1.04
     becoming
    -1.03
    poň
    -1.02
    POSITIVE LOGITS
     to
    2.13
     with
    1.28
     a
    1.08
     the
    1.07
     anew
    1.05
     by
    1.05
    –
    1.00
    新的
    0.99
    ел
    0.99
    endeu
    0.97
    Activations Density 0.026%

    No Known Activations