© 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. 6113
    Prev
    Next
    INDEX
    Explanations

    information referenced below

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

    The neuron detects directional reference words like “Above” and “Below” that introduce or point to adjacent content.

    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
    สมัย
    0.69
    ْت
    0.66
    OffsetX
    0.65
    아서
    0.64
    ن
    0.63
    OutOfBounds
    0.63
    ן
    0.63
    DialogOpen
    0.62
    achite
    0.59
    ueroa
    0.59
    POSITIVE LOGITS
    mentioned
    1.08
    👇
    1.03
     abaixo
    0.97
     👇
    0.96
    below
    0.93
     ниже
    0.90
    👆
    0.90
     below
    0.89
     reproach
    0.89
     ↓
    0.85
    Activations Density 0.105%

    No Known Activations