© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6549
    Prev
    Next
    INDEX
    Explanations

    such before harmful or forbidden actions

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

    The neuron primarily activates on the word “such” when used as an intensifier.

    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
     such
    0.71
    ag
    0.70
     、
    0.70
     both
    0.69
     دونوں
    0.68
     someth
    0.67
    有一些
    0.67
    en
    0.66
    oy
    0.65
     fuch
    0.65
    POSITIVE LOGITS
     coisa
    0.99
    like
    0.89
    ا
    0.88
     явления
    0.80
    THING
    0.79
    わけで
    0.77
    მ
    0.76
     thing
    0.75
    liko
    0.75
     DEVICES
    0.75
    Activations Density 0.371%

    No Known Activations