© 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. 10-GEMMASCOPE-RES-131K
    7. 129167
    Prev
    Next
    INDEX
    Explanations

    hex and numbers

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

    The neuron is detecting numeric literals (particularly floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -1.86
     ..."
    -1.70
     دقیقه
    -1.69
    transQ
    -1.64
     disfrut
    -1.59
     soort
    -1.59
     soñ
    -1.59
    ９
    -1.58
     amenaz
    -1.55
    。"
    -1.55
    POSITIVE LOGITS
     also
    1.66
     however
    1.58
    re
    1.53
     considered
    1.51
    a
    1.45
    いますが
    1.43
    を行
    1.42
    ですが
    1.38
     机械
    1.38
     explained
    1.36
    Activations Density 0.013%

    No Known Activations