© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7102
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

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

    The neuron is primarily detecting floating‐point number tokens (i.e. numerical values with decimal points).

    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_31_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
     клави
    0.87
    зіно
    0.80
     cadena
    0.80
     combatir
    0.79
     hicimos
    0.77
     caminar
    0.77
    쭐
    0.77
     returnMe
    0.77
    ی
    0.77
    ﻝ
    0.77
    POSITIVE LOGITS
    או
    0.67
     -
    0.63
     among
    0.63
     によって
    0.63
     Abstand
    0.61
     \&
    0.60
     Phone
    0.59
     ஆப
    0.59
    ```
    0.59
     atque
    0.59
    Activations Density 0.000%

    No Known Activations