© 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. 22-GEMMASCOPE-RES-131K
    7. 34035
    Prev
    Next
    INDEX
    Explanations

    criticism, outburst, split, issue

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

    The neuron fires strongly on capitalized named entities (people, places, organizations) in the text.

    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
     freakin
    -1.10
    0
    -1.05
     Thankfully
    -1.00
    tt
    -1.00
    o
    -0.99
     dessa
    -0.98
    O
    -0.98
    5
    -0.98
     Either
    -0.97
    她就
    -0.96
    POSITIVE LOGITS
     it
    1.27
    ִּ
    1.18
     joyería
    1.17
    ₓ
    1.16
    ַּ
    1.14
    şu
    1.13
     manualidades
    1.12
    penis
    1.12
    recently
    1.11
    ּוֹ
    1.11
    Activations Density 0.103%

    No Known Activations