© 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. 118189
    Prev
    Next
    INDEX
    Explanations

    Circuit, protocol, sequencing, structure, normalization

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

    The neuron is highly sensitive to tokens containing digits (i.e. numeric strings or alphanumeric identifiers).

    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
    сль
    -0.79
    wj
    -0.78
    visionnement
    -0.77
     Má
    -0.73
     kuni
    -0.72
    tubers
    -0.71
    kými
    -0.71
     soaps
    -0.70
    нут
    -0.70
     also
    -0.70
    POSITIVE LOGITS
    𐌹
    0.79
    ünchen
    0.79
    idikan
    0.75
     nanop
    0.73
     mindless
    0.72
     graves
    0.72
     [''],
    0.72
    reeg
    0.71
     rencontrer
    0.71
    atro
    0.71
    Activations Density 0.000%

    No Known Activations