© 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. 84168
    Prev
    Next
    INDEX
    Explanations

    method/function calls

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

    This neuron fires on CamelCase code identifiers (class names, method names, and other mixed-case tokens).

    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
     there
    -1.63
     including
    -1.45
    There
    -1.26
     will
    -1.23
     摆
    -1.09
     там
    -1.08
     gravure
    -1.05
    四月
    -1.03
     understand
    -1.02
     relating
    -1.02
    POSITIVE LOGITS
    差不
    1.26
     beendet
    1.12
     fijn
    1.09
     tendances
    1.08
     wereld
    1.08
     vraiment
    1.08
     verwendet
    1.07
     gefertigt
    1.07
    んだから
    1.07
    휀
    1.06
    Activations Density 0.075%

    No Known Activations