© 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. 84225
    Prev
    Next
    INDEX
    Explanations

    paths containing scripts

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

    The neuron primarily activates on numeric tokens and numeric expressions (digits, numbers, and simple arithmetic symbols).

    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
    цией
    -0.92
    ябре
    -0.88
     HSV
    -0.88
    ovací
    -0.88
    ября
    -0.85
    anches
    -0.82
    wahl
    -0.82
     tiki
    -0.80
     Krü
    -0.79
     Orbital
    -0.79
    POSITIVE LOGITS
     gold
    0.94
     smelling
    0.93
     adjacent
    0.85
     smell
    0.83
    glitter
    0.81
     fragrant
    0.79
     золото
    0.78
    princess
    0.76
     Birmingham
    0.75
     Gold
    0.74
    Activations Density 0.009%

    No Known Activations