© 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. 22-GEMMASCOPE-RES-131K
    7. 66976
    Prev
    Next
    INDEX
    Explanations

    committed to academic

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

    The neuron detects formal institutional or organizational statements—e.g. mission/policy language about commitments, services, or resources.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     by
    -1.41
    5
    -1.16
    0
    -1.15
    俱
    -1.15
     now
    -1.13
     from
    -1.13
     still
    -1.12
     Germany
    -1.12
    ('../
    -1.10
     Cantidad
    -1.10
    POSITIVE LOGITS
     foglie
    1.48
    Jahre
    1.37
    ktory
    1.35
    дован
    1.34
    Марина
    1.33
    Наталья
    1.30
     interrom
    1.30
    ässä
    1.28
    érrez
    1.27
    jenigen
    1.26
    Activations Density 0.011%

    No Known Activations