© 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. 34-GEMMASCOPE-RES-131K
    7. 59587
    Prev
    Next
    INDEX
    Explanations

    references to things above

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

    This neuron detects spatial-reference words used in instructional text, such as “above” and “below,” that point the reader to UI elements.

    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
     below
    -1.24
    AppRoutingModule
    -1.00
    スポンサーリンク
    -0.97
     aşağı
    -0.96
     like
    -0.95
    Ἢ
    -0.94
    erdere
    -0.91
     hail
    -0.89
     onderstaande
    -0.88
    rrggbb
    -0.87
    POSITIVE LOGITS
     👆
    1.34
    หน้านี้
    1.08
    👆
    1.00
    只不过
    0.96
    換え
    0.93
    これを
    0.93
    this
    0.93
    ⇑
    0.91
     paragraph
    0.91
     paragraphs
    0.89
    Activations Density 0.047%

    No Known Activations