© 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. 149
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on first‐person pronouns or personal “I” statements in the text.

    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
    さまざまな
    0.46
     величе
    0.44
    <unused450>
    0.44
    <unused2180>
    0.43
    私たち
    0.42
     জনগণের
    0.42
    <unused990>
    0.40
    <unused2173>
    0.40
    <unused325>
    0.40
     hereinafter
    0.39
    POSITIVE LOGITS
     agree
    0.78
    agree
    0.77
     Agree
    0.72
     goog
    0.68
    Agree
    0.66
     sorry
    0.65
     congrats
    0.64
     আমিও
    0.64
     dunno
    0.64
     Ebay
    0.63
    Activations Density 2.060%

    No Known Activations