© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27325
    Prev
    Next
    INDEX
    Explanations

    increased or higher values

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

    The neuron detects comparative or quantitative words expressing increased magnitude or degree (e.g. higher, increased, greater, larger, better).

    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
    varies
    -1.20
    )=>{
    -1.14
     cordones
    -1.10
    werpen
    -1.09
     pilas
    -1.06
    parfum
    -1.01
    zdo
    -0.99
     effets
    -0.98
     muchacha
    -0.98
     najbol
    -0.98
    POSITIVE LOGITS
     to
    1.34
     will
    1.14
     in
    1.10
    機會
    0.92
     枚
    0.91
     官方
    0.91
     模板
    0.88
     needs
    0.86
     ariel
    0.85
     enough
    0.84
    Activations Density 0.074%

    No Known Activations