© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5660
    Prev
    Next
    INDEX
    Explanations

    null injector error

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

    The neuron strongly activates on proper names (people, places, organizations) and other named-entity tokens.

    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
    arrêt
    0.58
     Nope
    0.56
    eigen
    0.55
    檴
    0.55
     तप
    0.54
    Nope
    0.54
     imply
    0.54
     млрд
    0.53
     nope
    0.53
    indications
    0.53
    POSITIVE LOGITS
    Broad
    0.60
    പ്പെടെ
    0.59
     Broad
    0.57
    oreau
    0.53
     Verne
    0.52
     wur
    0.52
    supabase
    0.52
     Rashifal
    0.51
    仝
    0.51
    ridos
    0.50
    Activations Density 0.276%

    No Known Activations