© 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. 1339
    Prev
    Next
    INDEX
    Explanations

    file downloads and sizes

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

    The neuron activates on numeric sequences (multi‐digit numbers or numeric tokens).

    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
    iança
    -0.83
    Personendaten
    -0.81
    Siapa
    -0.81
     снег
    -0.77
    生平
    -0.77
    лав
    -0.75
    orative
    -0.74
    olda
    -0.74
     thereafter
    -0.74
     NDC
    -0.73
    POSITIVE LOGITS
    boyfriend
    0.85
    zahlen
    0.84
    Tore
    0.83
     Mime
    0.82
    phoria
    0.80
    ловая
    0.80
    _-_
    0.79
    Mime
    0.77
     Size
    0.77
     adverten
    0.77
    Activations Density 0.020%

    No Known Activations