© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions

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

    The neuron detects spatial‐relation prepositions that indicate directions or positions (e.g. “above,” “over,” “around,” “down,” “across,” etc.).

    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
     '
    0.65
    ק
    0.64
     وفق
    0.64
     kanssa
    0.63
     viac
    0.63
     באמצעות
    0.63
     באופן
    0.61
     таком
    0.60
     "":
    0.60
     Ciencias
    0.60
    POSITIVE LOGITS
     treetops
    0.85
     sawmill
    0.75
    sthe
    0.72
     embankment
    0.72
     دیوار
    0.72
    ünün
    0.70
     paddock
    0.70
    The
    0.69
     curving
    0.69
    侧
    0.69
    Activations Density 0.095%

    No Known Activations