© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 759
    Prev
    Next
    INDEX
    Explanations

    The neuron detects instructional “how-to” or tutorial cue phrases (e.g. “learn how to,” “how you can…”) signaling that the text is giving directions or teaching how to do 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
     impregnated
    0.73
     comunque
    0.66
    1
    0.64
     опубликова
    0.64
     overheard
    0.64
     sabot
    0.63
     показ
    0.63
     collaborators
    0.63
     увидел
    0.63
     crept
    0.62
    POSITIVE LOGITS
     Yous
    0.71
    看待
    0.68
    技术的
    0.65
    soever
    0.64
    Tính
    0.64
    matig
    0.63
    Қ
    0.63
     如何
    0.61
    Tienes
    0.61
     يمكنك
    0.61
    Activations Density 0.085%

    No Known Activations