© 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. 9744
    Prev
    Next
    INDEX
    Explanations

    handling design description chain base

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

    The neuron is looking for numeric tokens (numbers, measurements, or other digit sequences).

    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
    ம
    0.63
    ﻧ
    0.63
    ре
    0.60
    ध
    0.60
    ୬
    0.60
     мото
    0.59
    ﮐ
    0.59
    夰
    0.58
    ری
    0.58
    㭉
    0.58
    POSITIVE LOGITS
     extraordinaire
    0.96
     extravag
    0.59
     extras
    0.57
    和社会
    0.57
     extravagance
    0.55
     essentials
    0.54
     enthusiast
    0.54
     adventures
    0.53
     staples
    0.52
    を超
    0.51
    Activations Density 1.155%

    No Known Activations