© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9032
    Prev
    Next
    INDEX
    Explanations

    Think of it like

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

    The neuron is detecting numeric tokens that include decimal points (i.e., 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
    Для
    0.69
    知らせ
    0.69
    VAR
    0.67
    ཝ
    0.67
     वापर
    0.66
    сть
    0.66
    예
    0.64
     পশ্চিমবঙ্গ
    0.64
    ંમે
    0.64
    힐
    0.64
    POSITIVE LOGITS
    𝘥
    0.78
    );
    0.72
     cameos
    0.71
    ᱗
    0.71
     Strukturen
    0.70
     instalments
    0.69
    >-->
    0.69
     kesulitan
    0.69
     desa
    0.68
     aport
    0.67
    Activations Density 0.000%

    No Known Activations