© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    code documentation structure

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

    The neuron strongly activates on the word “away.”

    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
    $;
    0.81
    ח
    0.80
     olds
    0.75
    х
    0.73
    ERA
    0.73
    mitter
    0.73
     strs
    0.71
    ные
    0.68
    分け
    0.68
    %；
    0.67
    POSITIVE LOGITS
     organizing
    0.79
     robbed
    0.75
    vano
    0.74
     deprived
    0.72
     внесен
    0.72
    katan
    0.71
     याबाबत
    0.71
     domicili
    0.71
     penned
    0.70
    ρει
    0.69
    Activations Density 0.000%

    No Known Activations