© 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. 77471
    Prev
    Next
    INDEX
    Explanations

    code comments and licenses

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

    The neuron strongly activates on numeric expressions (years, counts, measurements) and related quantitative data in the text.

    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
    洁
    -0.83
     phản
    -0.78
    นำ
    -0.73
    quido
    -0.73
    Jr
    -0.69
    сной
    -0.69
     Councillor
    -0.68
    ortunadamente
    -0.67
    可选
    -0.67
     Wix
    -0.66
    POSITIVE LOGITS
     SZ
    0.81
    LIM
    0.80
    nian
    0.79
    čnega
    0.79
     союз
    0.77
    Penulis
    0.77
    Drive
    0.76
     candidatura
    0.76
    HEAT
    0.75
     Sert
    0.75
    Activations Density 0.010%

    No Known Activations