© 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. 10-GEMMASCOPE-RES-131K
    7. 15205
    Prev
    Next
    INDEX
    Explanations

    pen names

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

    The neuron activates on words referring to manual writing tools or materials (e.g. pen, quill, ink, vellum, manuscript).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     you
    -2.05
     ditt
    -1.62
     ‘
    -1.55
     hunde
    -1.52
     minder
    -1.51
     []:
    -1.50
     rigue
    -1.48
    ﮨ
    -1.43
     überhaupt
    -1.41
     gese
    -1.40
    POSITIVE LOGITS
     February
    1.51
     first
    1.41
     bazı
    1.41
     expands
    1.41
     撮っ
    1.34
     本店
    1.34
     decreases
    1.33
     partly
    1.32
    ڤ
    1.31
    راع
    1.30
    Activations Density 0.018%

    No Known Activations