© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13373
    Prev
    Next
    INDEX
    Explanations

    facing against enemies

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

    This neuron responds to specialized scientific or technical jargon and numeric data—particularly long, multi-syllabic nouns (like “multivalency,” “ligands”) and numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ALSO
    -0.93
    ově
    -0.82
     verdadero
    -0.81
    GetComponent
    -0.81
    VARIANT
    -0.79
     THERE
    -0.78
    uxxxx
    -0.77
    Ϯ
    -0.75
    EDT
    -0.75
    ATURA
    -0.75
    POSITIVE LOGITS
     against
    1.58
     gegenüber
    1.37
     против
    1.15
     melawan
    1.09
     enemies
    1.09
     menghadapi
    1.08
     enemy
    1.07
    面对
    1.05
    against
    1.04
     facing
    1.03
    Activations Density 0.126%

    No Known Activations