© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69178
    Prev
    Next
    INDEX
    Explanations

    looking for something

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

    The neuron detects “looking for” requests specifying particular data files or resources.

    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
    ACIO
    -1.03
    pæ
    -1.03
     strikingly
    -1.02
     wonderfully
    -0.98
     diámetro
    -0.98
     hormigón
    -0.97
     ตัว
    -0.94
     mostrando
    -0.94
     choisi
    -0.94
     vastly
    -0.94
    POSITIVE LOGITS
     to
    1.81
     in
    1.36
     information
    1.34
     suitable
    1.31
     while
    1.28
     new
    1.21
     out
    1.20
     ways
    1.20
    答案
    1.15
     because
    1.14
    Activations Density 0.089%

    No Known Activations