© 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. 1284
    Prev
    Next
    INDEX
    Explanations

    The neuron is essentially keyed to the directional preposition “towards.”

    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
    ৮
    0.76
    ين
    0.66
    ни
    0.63
    ка
    0.61
    ک
    0.58
    น
    0.55
    ীর
    0.55
    те
    0.54
    त्
    0.53
    ње
    0.52
    POSITIVE LOGITS
     Hrvatskoj
    0.59
    不已
    0.59
    volving
    0.58
     sposób
    0.56
    akumar
    0.55
    ㊙
    0.55
    他的
    0.55
    삶
    0.55
     самой
    0.54
     kroppen
    0.54
    Activations Density 0.000%

    No Known Activations