© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8268
    Prev
    Next
    INDEX
    Explanations

    I cannot fulfill this request

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

    This neuron detects first-person opinion phrases (e.g. “What I think,” “I love,” etc.).

    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
     thinks
    0.64
    things
    0.59
    Everything
    0.57
    everything
    0.57
    ޝ
    0.55
     everything
    0.55
     topics
    0.55
     EVERYTHING
    0.54
     இருக்கலாம்
    0.54
     think
    0.54
    POSITIVE LOGITS
     También
    0.70
    También
    0.68
     también
    0.63
     cũng
    0.61
     लक्षात
    0.60
    也
    0.59
    も見
    0.59
     lacked
    0.58
    Notice
    0.57
     also
    0.57
    Activations Density 0.188%

    No Known Activations