© 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. 34-GEMMASCOPE-RES-131K
    7. 2591
    Prev
    Next
    INDEX
    Explanations

    words starting with anti-

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

    The neuron activates on occurrences of the prefix “anti” (especially in hyphenated compounds).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     philanthropy
    -0.81
    ද
    -0.79
    CloseHandle
    -0.76
     wea
    -0.72
    ället
    -0.70
    ÁCT
    -0.69
    𝙏
    -0.68
     CX
    -0.68
    GUN
    -0.68
     anzu
    -0.67
    POSITIVE LOGITS
    clockwise
    0.89
     crudo
    0.77
    rero
    0.74
    漪
    0.73
     concreto
    0.73
    allar
    0.72
    Aircraft
    0.72
     [@
    0.71
    inkite
    0.71
     narcotics
    0.71
    Activations Density 0.032%

    No Known Activations