© 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. 34-GEMMASCOPE-RES-131K
    7. 63628
    Prev
    Next
    INDEX
    Explanations

    passes tests

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

    The neuron fires on terminology related to testing or evaluation—words about conducting tests and judging pass/fail results.

    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
     começaram
    -0.76
    ēr
    -0.70
    到着
    -0.68
    endetta
    -0.68
    ulls
    -0.68
    effectiveness
    -0.67
     ง
    -0.65
    seb
    -0.65
    itah
    -0.64
    chemin
    -0.63
    POSITIVE LOGITS
     passed
    6.13
     passing
    5.63
     passes
    5.09
     pass
    5.06
    passed
    4.97
     Passed
    4.81
    Passed
    4.81
     Passing
    4.69
    Passing
    4.63
    passing
    4.47
    Activations Density 0.125%

    No Known Activations