© 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. 22-GEMMASCOPE-RES-131K
    7. 26563
    Prev
    Next
    INDEX
    Explanations

    necessity and urgency

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

    The neuron specializes in picking out numeric values or measurements (tokens containing numbers) in the text.

    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
     tetrachloride
    -0.93
    tween
    -0.92
     Metacritic
    -0.90
     lasci
    -0.89
    hope
    -0.88
    sont
    -0.88
    arina
    -0.86
    Ena
    -0.86
    őbb
    -0.86
    attempt
    -0.85
    POSITIVE LOGITS
     necessity
    1.24
     urgency
    1.09
     need
    1.03
     motivation
    1.02
     stress
    1.00
     motivates
    0.98
     needing
    0.95
     necessitated
    0.94
     motivate
    0.94
     justification
    0.91
    Activations Density 0.098%

    No Known Activations