© 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. 22-GEMMASCOPE-RES-131K
    7. 32987
    Prev
    Next
    INDEX
    Explanations

    Australian Signals Q:

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

    The neuron strongly responds to the standalone digit “2,” i.e. occurrences of the numeral 2 in numeric 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_22/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
     либо
    -1.00
     Республи
    -0.98
    ých
    -0.97
     jobb
    -0.94
     kell
    -0.91
     باید
    -0.91
     jó
    -0.90
    暂无
    -0.89
     jener
    -0.88
    whom
    -0.88
    POSITIVE LOGITS
     verschiedener
    1.24
     laikā
    1.14
     hinsichtlich
    1.09
     papild
    1.02
     wanting
    1.01
     uscire
    0.99
    ত্র
    0.99
    oczes
    0.98
    であるが
    0.98
     contraseña
    0.97
    Activations Density 0.000%

    No Known Activations