© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128269
    Prev
    Next
    INDEX
    Explanations

    direction or inclination

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

    This neuron detects words and phrases that indicate bias or directional “leanings” (e.g. lean, towards, skew).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    我們
    -1.71
     Ironically
    -1.70
    ovács
    -1.65
    rália
    -1.62
     нам
    -1.53
     видно
    -1.52
     Dicapai
    -1.51
     Basically
    -1.48
     Regardless
    -1.48
     Despite
    -1.48
    POSITIVE LOGITS
    蟥
    1.66
    婓
    1.66
     likely
    1.61
    V
    1.61
    ,.
    1.61
    ,;
    1.60
     becoming
    1.60
    先に
    1.58
     ،
    1.57
    ことも
    1.51
    Activations Density 0.019%

    No Known Activations