© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65542
    Prev
    Next
    INDEX
    Explanations

    stag, stage, stigma, stag leap

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

    The neuron strongly activates on any token containing the four‐letter sequence “stag” or its close variant “stig,” catching words like “Stag,” “stag,” “stagnating,” and “stigma.”

    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
     groin
    -0.81
    猹
    -0.77
     FON
    -0.75
     COLLINS
    -0.75
     KN
    -0.74
     clowns
    -0.74
    蕖
    -0.72
    otechnical
    -0.72
     باشی
    -0.70
     compréhension
    -0.69
    POSITIVE LOGITS
     Stag
    1.25
    Stag
    1.08
     stag
    1.07
     Leap
    0.98
    stag
    0.97
    Leap
    0.79
     salto
    0.73
     leap
    0.73
     coach
    0.72
     本
    0.72
    Activations Density 0.023%

    No Known Activations