© 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. 6187
    Prev
    Next
    INDEX
    Explanations

    this document/class/driver/table/policy/plan

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

    The neuron is highly sensitive to demonstrative determiners—especially “This” (and to a lesser extent “These”)—at the start of sentences.

    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
    Buscar
    0.69
    QUERY
    0.68
    。
    0.67
    TOK
    0.67
     数字
    0.66
    几种
    0.66
     比
    0.65
    жидан
    0.65
    ↘
    0.65
    ToInt
    0.64
    POSITIVE LOGITS
     microorganism
    0.82
     multipurpose
    0.80
     prides
    0.78
     incorporates
    0.78
     polycrystalline
    0.73
     eliminates
    0.73
     equestrian
    0.71
     reduces
    0.71
     allows
    0.71
     resembles
    0.70
    Activations Density 0.133%

    No Known Activations