© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99617
    Prev
    Next
    INDEX
    Explanations

    research project numbers

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

    The neuron responds strongly to occurrences of the standalone digit “0.”

    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
     balade
    -0.95
     still
    -0.93
     lainnya
    -0.93
    Still
    -0.91
     вашем
    -0.90
    Never
    -0.85
    <<(
    -0.85
    hintText
    -0.85
     prefent
    -0.85
    私は
    -0.85
    POSITIVE LOGITS
    0
    1.72
    onavirus
    0.96
    dibility
    0.94
    ctor
    0.92
     unserer
    0.91
    silien
    0.90
     Erfüllung
    0.89
    caster
    0.89
    heet
    0.89
    tape
    0.87
    Activations Density 0.084%

    No Known Activations