© 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. 92506
    Prev
    Next
    INDEX
    Explanations

    repeat together or zero times

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

    The neuron fires on numeric tokens or digit sequences (e.g. numbers in XML attributes, regex quantifiers, code literals).

    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
    SceneManagement
    -0.81
    silience
    -0.77
     flimsy
    -0.75
    landt
    -0.74
    蔔
    -0.74
     Bloomington
    -0.73
     simplu
    -0.73
    assies
    -0.73
     unwavering
    -0.71
    واء
    -0.71
    POSITIVE LOGITS
     zero
    1.35
    Zero
    1.23
    zero
    1.22
     minOccurs
    1.20
     repeat
    1.18
     Zero
    1.17
     ZERO
    1.12
     repetition
    1.10
    repeat
    1.05
    Repeat
    1.04
    Activations Density 0.025%

    No Known Activations