© 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. 82870
    Prev
    Next
    INDEX
    Explanations

    technical documentation sections

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

    The neuron strongly activates on numeric tokens and associated markup (e.g. version or section numbers and HTML tag delimiters).

    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
     különböz
    -0.98
    *}$
    -0.91
    }\,\
    -0.87
     tapasztal
    -0.87
    さも
    -0.86
     kérd
    -0.83
     cheia
    -0.81
     towarzys
    -0.80
     lukisan
    -0.80
     erős
    -0.80
    POSITIVE LOGITS
    Réalisation
    1.04
    mentet
    1.02
    retour
    0.96
     cerim
    0.94
    Vä
    0.94
    ordum
    0.93
    uição
    0.93
    выми
    0.92
     thr
    0.90
    entyfik
    0.90
    Activations Density 0.049%

    No Known Activations