© 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. 667
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on past-tense or past-participle verb forms (especially in passive‐voice or “be + participle” constructions).

    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
    꾼
    0.45
    ోంది
    0.43
    的时候
    0.42
     اوم
    0.42
     خونه
    0.42
     받은
    0.42
    GetType
    0.41
     बीते
    0.41
     بودن
    0.41
     लेके
    0.41
    POSITIVE LOGITS
    および
    0.65
     および
    0.62
    .\\
    0.57
     மற்றும்
    0.55
    ។
    0.52
    ܀
    0.52
    یں۔
    0.52
     Более
    0.52
    ؛
    0.51
     તેમજ
    0.51
    Activations Density 0.000%

    No Known Activations