© 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. 13354
    Prev
    Next
    INDEX
    Explanations

    quantifying or approximating

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

    This neuron detects words that refer to offering or requesting “details” or “information” (e.g. “these details,” “this information”).

    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
    에
    0.90
    ك
    0.82
    tex
    0.81
    şt
    0.81
    tx
    0.80
    ἐ
    0.80
    px
    0.80
    blogspot
    0.79
    х
    0.79
    还是
    0.78
    POSITIVE LOGITS
     livelihoods
    0.83
     tapes
    0.82
     wasteland
    0.81
     sugarcane
    0.80
     overlap
    0.80
     unicorns
    0.77
     midterm
    0.75
    ATURE
    0.75
     tools
    0.75
     punctures
    0.75
    Activations Density 0.001%

    No Known Activations