© 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. 48315
    Prev
    Next
    INDEX
    Explanations

    conclusions published

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

    The neuron is primarily firing on numeric tokens (i.e. digits, dates, counts, and other number sequences).

    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
     bạch
    -0.83
    Casper
    -0.82
     probabil
    -0.82
    ildes
    -0.81
    全新的
    -0.79
    过去了
    -0.79
    ELECTRON
    -0.79
     capac
    -0.78
    andolo
    -0.77
     новым
    -0.76
    POSITIVE LOGITS
     should
    0.81
     млн
    0.78
    ⅽ
    0.76
     Thron
    0.75
    bang
    0.74
    pump
    0.73
    BE
    0.73
     amg
    0.72
     bang
    0.71
     GUR
    0.70
    Activations Density 0.000%

    No Known Activations