© 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. 72865
    Prev
    Next
    INDEX
    Explanations

    US Pat No

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

    The neuron fires on numeric tokens (digits and multi‐digit numbers) 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_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
    ”),
    -0.96
    听了
    -0.94
    際には
    -0.92
     twij
    -0.92
     juillet
    -0.90
     soñ
    -0.89
    anneau
    -0.89
    つづく
    -0.86
     secuen
    -0.85
     lucht
    -0.85
    POSITIVE LOGITS
    avajillas
    0.91
    ゾ
    0.87
     clams
    0.84
     delt
    0.83
    atud
    0.82
    прави
    0.82
    や
    0.81
     basa
    0.81
    基本的
    0.80
    <bos>
    0.79
    Activations Density 0.039%

    No Known Activations