© 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. 3774
    Prev
    Next
    INDEX
    Explanations

    these, this, dieser, diese, aceste, cette, deze, this (demonstratives)

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

    The neuron activates on terms describing project planning or scheduling activities—words like “drafted,” “plan,” “planning,” and “scheduling.”

    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
    ൪
    0.72
     слабо
    0.69
    我自己
    0.66
     термо
    0.65
     นึง
    0.64
     брау
    0.64
    ጶ
    0.64
     воду
    0.63
    一種
    0.63
    ྭ
    0.63
    POSITIVE LOGITS
     these
    1.27
     this
    1.23
     aceste
    1.12
     diese
    1.04
     cette
    1.02
     deze
    1.02
     dieser
    1.01
    these
    1.00
     هذه
    0.99
     මෙම
    0.99
    Activations Density 1.843%

    No Known Activations