© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10954
    Prev
    Next
    INDEX
    Explanations

    uploading digital content or photos

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

    the past tense verb "uploaded" in contexts describing digital file transfers or content posting.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by mentions of “upload” (especially “uploaded” or “uploading”) indicating that content (files, images, videos, etc.) has been uploaded.

    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
    It
    -2.50
    }$
    -2.38
     così
    -2.17
    0
    -2.11
     nawet
    -2.00
    S
    -2.00
     verstanden
    -1.98
    That
    -1.97
    st
    -1.96
    __":
    -1.93
    POSITIVE LOGITS
    鸶
    2.28
    穑
    2.25
    懌
    2.14
    倓
    2.13
     compradores
    2.09
     a
    2.09
    𓆜
    2.09
     inversores
    2.08
    套路
    2.06
    鳊
    2.05
    Activations Density 0.011%

    No Known Activations