© 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. 9792
    Prev
    Next
    INDEX
    Explanations

    transaction. commit. post. Taxes. anticancer drug. from. await

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

    The neuron activates on numeric tokens containing a decimal point (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
    1.36
    1
    1.30
    8
    1.22
    2
    1.16
    5
    1.14
    4
    1.10
    3
    1.07
    7
    1.07
    9
    1.02
    6
    0.96
    POSITIVE LOGITS
    CTOGRAM
    0.95
     جنت
    0.91
    કિસ્
    0.91
    ἀ
    0.89
    缃
    0.89
    وڑا
    0.88
    伍章
    0.88
    <unused52>
    0.86
    igamma
    0.86
    ᴦ
    0.85
    Activations Density 0.000%

    No Known Activations