© 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. 34-GEMMASCOPE-RES-131K
    7. 30684
    Prev
    Next
    INDEX
    Explanations

    most above all

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

    The neuron activates on numeric tokens (multi‐digit 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_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
    ならでは
    -0.95
     many
    -0.93
     одни
    -0.93
     gyak
    -0.91
    many
    -0.90
     tourné
    -0.90
     often
    -0.90
    ならではの
    -0.90
     wtedy
    -0.88
     чему
    -0.88
    POSITIVE LOGITS
     most
    5.31
     above
    3.48
    Most
    3.33
     главное
    3.22
    most
    3.16
    何より
    3.09
     soprattutto
    3.06
     самое
    3.00
    Above
    2.89
     przede
    2.88
    Activations Density 0.091%

    No Known Activations