© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84561
    Prev
    Next
    INDEX
    Explanations

    court document headers

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

    This neuron detects occurrences of “memo” (in any form, e.g. in names like memoize or headers like MEMORANDUM).

    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
    tacle
    -0.91
    褫
    -0.88
    indeed
    -0.84
    conditioning
    -0.80
     पढ़
    -0.80
    不满
    -0.79
    为自己
    -0.79
     kuwa
    -0.79
    itisation
    -0.79
    实习
    -0.78
    POSITIVE LOGITS
     purely
    0.80
     information
    0.77
    鉉
    0.77
     expelled
    0.73
     WebElement
    0.73
     airtight
    0.72
    esía
    0.71
    nehå
    0.70
     Organized
    0.70
     дослі
    0.69
    Activations Density 0.003%

    No Known Activations