© 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. 197
    Prev
    Next
    INDEX
    Explanations

    key-value assignments

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

    The neuron triggers on technical tokens like configuration flags, URL query parameter names, and associated numeric values in code or link fragments.

    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
    殞
    0.22
    चाकी
    0.21
     উদ্ভিদ
    0.21
     ২৭
    0.21
     పదార్థ
    0.21
     কীট
    0.21
     различи
    0.21
    हीत
    0.20
    მასრულ
    0.20
     ලද
    0.20
    POSITIVE LOGITS
     =
    0.36
    :
    0.32
    =
    0.30
    ="
    0.28
    =\
    0.26
    ：
    0.25
    ='
    0.22
    ="-
    0.22
     :
    0.21
     =\
    0.21
    Activations Density 0.016%

    No Known Activations