© 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. 98255
    Prev
    Next
    INDEX
    Explanations

    additional turn

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

    The neuron fires on numeric references and quantity expressions (digits and count words).

    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
     вчера
    -0.84
    ément
    -0.73
    today
    -0.73
     terapi
    -0.73
    prü
    -0.73
    ří
    -0.72
     serán
    -0.71
    TIT
    -0.71
    yesterday
    -0.71
    Today
    -0.70
    POSITIVE LOGITS
     turn
    3.84
     turns
    3.13
    turn
    2.86
    Turn
    2.73
     Turn
    2.73
     Turns
    2.22
     TURN
    2.22
     turno
    2.16
    turns
    2.16
    TURN
    2.09
    Activations Density 0.031%

    No Known Activations