© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64785
    Prev
    Next
    INDEX
    Explanations

    Plain English

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

    The neuron fires on JavaScript/TypeScript test‐framework setup hooks—especially “beforeEach” calls (and their accompanying arrow/function definitions).

    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
    doctrine
    -0.86
     igre
    -0.84
    balanceOf
    -0.81
     Spiele
    -0.81
     chapéu
    -0.80
     હ
    -0.79
     dout
    -0.78
     eventi
    -0.77
     Spielen
    -0.76
    crystalline
    -0.76
    POSITIVE LOGITS
     setups
    0.99
    }];
    0.81
     Jokes
    0.80
     initializing
    0.79
     setup
    0.78
     rewind
    0.77
     timezone
    0.74
    inez
    0.74
     expel
    0.73
    лиза
    0.73
    Activations Density 0.003%

    No Known Activations