© 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. 3628
    Prev
    Next
    INDEX
    Explanations

    approach or approaches

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

    The neuron activates on the word “approach,” marking when text describes a particular method or way of doing something.

    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
    ン
    1.18
    ATION
    1.17
     juist
    1.06
    n
    1.05
    ن
    1.03
    l
    1.02
     avail
    0.94
    baixo
    0.94
    sı
    0.93
    н
    0.92
    POSITIVE LOGITS
    主義
    1.23
    ية
    1.18
    ﯽ
    1.14
    मतौर
    1.12
    вати
    1.07
     तरीका
    1.06
     buscan
    1.05
    ным
    1.04
    ﻪ
    1.04
    ৫
    1.03
    Activations Density 0.013%

    No Known Activations