© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11047
    Prev
    Next
    INDEX
    Explanations

    KeepTweetclass

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

    This neuron responds to apostrophe‐containing tokens, i.e. contractions or possessives (words with ’).

    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
     massive
    0.59
     resources
    0.54
     cl
    0.53
     unrel
    0.52
     tools
    0.52
     d
    0.52
     numeros
    0.52
     foi
    0.51
     ressources
    0.51
     wors
    0.51
    POSITIVE LOGITS
    ŧ
    0.72
    ây
    0.70
    ఞ
    0.68
    ường
    0.68
    émor
    0.67
    Ľ
    0.66
    ốp
    0.65
    úc
    0.64
    út
    0.64
    áte
    0.64
    Activations Density 0.208%

    No Known Activations