© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84458
    Prev
    Next
    INDEX
    Explanations

    temperatures and units

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

    The neuron fires primarily on numeric constants—both integers and decimal numbers—wherever they appear.

    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
     only
    -1.76
     from
    -1.73
     But
    -1.59
    啻
    -1.49
    from
    -1.48
     bezieht
    -1.48
     ensin
    -1.46
    hhhhhhhh
    -1.45
    身上的
    -1.45
     it
    -1.44
    POSITIVE LOGITS
    德國
    1.67
    Didn
    1.65
    Kemudian
    1.51
    韓國
    1.50
    Something
    1.48
     abat
    1.45
    actéristi
    1.44
    Sometimes
    1.41
     and
    1.41
    Пере
    1.40
    Activations Density 0.002%

    No Known Activations