© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87046
    Prev
    Next
    INDEX
    Explanations

    code comments

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

    The neuron fires on standalone numeric or alphanumeric tokens containing digits (e.g. version numbers, years, IDs).

    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
     lignin
    -0.82
    KG
    -0.79
    getUsers
    -0.77
    ेत्र
    -0.72
    onej
    -0.70
     fructose
    -0.68
     UPM
    -0.68
    SAG
    -0.68
    ForUser
    -0.67
    観光
    -0.66
    POSITIVE LOGITS
    ){$\
    0.93
    Coverage
    0.74
     efficace
    0.74
    şan
    0.71
     rése
    0.69
    salad
    0.68
     confirmó
    0.67
     בד
    0.67
    "}"
    0.67
     qualifications
    0.66
    Activations Density 0.040%

    No Known Activations