© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7269
    Prev
    Next
    INDEX
    Explanations

    hope, hopefully, do

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

    The neuron is essentially inactive—it does not reliably respond to any 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
     INCREASE
    0.69
     ĝ
    0.65
     remastered
    0.65
    ↵↵
    0.64
     attrezz
    0.64
     DESCRIPTION
    0.63
     iš
    0.63
    ↵↵↵↵
    0.62
    ↵↵↵
    0.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.60
    POSITIVE LOGITS
    <h4>
    0.76
    Step
    0.75
    <h3>
    0.74
    <h1>
    0.71
    Form
    0.68
    Should
    0.68
    <h5>
    0.67
    Escol
    0.67
    Từ
    0.66
    <h2>
    0.66
    Activations Density 0.549%

    No Known Activations