© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2028
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    User
    0.64
    ian
    0.55
    ী
    0.54
    ют
    0.52
    Image
    0.47
    ется
    0.46
    <0xBC>
    0.45
    습니다
    0.45
    ate
    0.44
    ﻟ
    0.44
    POSITIVE LOGITS
    ties
    0.55
    지는
    0.54
     estern
    0.54
    가는
    0.51
    নৈতিক
    0.49
     gorges
    0.49
    ἢ
    0.47
    크
    0.46
    רים
    0.46
    itumor
    0.46
    Activations Density 0.000%

    No Known Activations