© 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. 34-GEMMASCOPE-RES-131K
    7. 30549
    Prev
    Next
    INDEX
    Explanations

    CSU, Learn, Cover, Sudden, In, child, Whether, Once

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

    The neuron fires on section headings or titles (often followed by a colon), marking the starts of major document sections.

    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
    
    -1.00
    ⸻
    -0.98
    ᴉ
    -0.93
     that
    -0.92
    ехать
    -0.90
    —–
    -0.87
    ૭
    -0.86
    ‎‎
    -0.85
     unseen
    -0.84
     genellikle
    -0.84
    POSITIVE LOGITS
     •
    3.58
    •
    3.25
     ·
    2.41
    
    2.39
    ·
    2.34
     
    2.28
    ・
    2.28
     ●
    2.27
    ●
    2.25
     -
    1.97
    Activations Density 0.136%

    No Known Activations