© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    achievable goals with numbers

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

    The neuron selectively activates on floating‐point numeric tokens (numbers with decimal points and multiple digits).

    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
     ૩
    0.61
     ١
    0.59
     ১৭
    0.58
     ૧
    0.56
     ৪
    0.55
     ১২
    0.55
     ১
    0.54
     ১৫
    0.54
     ۱
    0.54
     ১৮
    0.52
    POSITIVE LOGITS
     takeaways
    0.38
     crowdfunding
    0.38
    breadcrumbs
    0.38
     blockchains
    0.37
     avocados
    0.37
    rég
    0.37
    lo
    0.36
     emojis
    0.36
    തന്നെ
    0.36
     airspace
    0.36
    Activations Density 0.000%

    No Known Activations