© 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. 128557
    Prev
    Next
    INDEX
    Explanations

    concerned with

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

    This neuron fires on the fixed phrase “concerned with.”

    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
    );
    -2.31
    2
    -1.79
     bloated
    -1.76
     rebuke
    -1.75
     a
    -1.73
    ᥬ
    -1.73
     are
    -1.70
    常に
    -1.63
    我們的
    -1.61
    顔が
    -1.60
    POSITIVE LOGITS
     and
    2.00
    at
    1.97
    </em>
    1.96
    og
    1.76
    AdvEx
    1.74
    m
    1.71
    लाइन
    1.65
    n
    1.60
    ing
    1.60
    ↵
    1.60
    Activations Density 0.006%

    No Known Activations