© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12456
    Prev
    Next
    INDEX
    Explanations

    salutations or questions

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

    This neuron activates on social-media–style image announcements or captions (e.g. tokens like “pic,” “from,” and day names) indicating a post sharing a photo.

    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
     uten
    0.59
    
    0.59
     केसांना
    0.57
    सुद्धा
    0.57
    »)
    0.56
     spectacles
    0.56
    зора
    0.56
     ultraviolet
    0.55
     kilogram
    0.55
    或者是
    0.55
    POSITIVE LOGITS
     #
    1.73
     @
    1.61
     \#
    1.17
    #
    1.09
    .@
    1.06
    @
    1.05
     (@
    1.02
     @_
    1.00
     đc
    1.00
    ってる
    0.96
    Activations Density 0.081%

    No Known Activations