© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11621
    Prev
    Next
    INDEX
    Explanations

    (i, j) matrix indices

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

    The neuron fires on words that head multiword relational constructions—i.e. words like “result,” “akin,” “away,” “within,” “direction,” etc., when they introduce a following prepositional phrase.

    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_31_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
    2
    0.70
    4
    0.62
    3
    0.58
     asymmetric
    0.55
    _{-
    0.54
    7
    0.54
     $
    0.53
    1
    0.52
    9
    0.52
    6
    0.52
    POSITIVE LOGITS
    θεση
    0.66
     theſe
    0.64
     Surveys
    0.61
     Districts
    0.59
     Placement
    0.59
    ulaires
    0.59
     thefe
    0.58
     kormány
    0.58
     Botan
    0.57
     Wachstum
    0.57
    Activations Density 0.001%

    No Known Activations