© 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. 22-GEMMASCOPE-RES-131K
    7. 73701
    Prev
    Next
    INDEX
    Explanations

    modified, adapted, or updated

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

    The neuron fires on specialized technical or academic terminology and phrasing characteristic of formal method or design descriptions.

    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
     each
    -1.21
     all
    -1.16
     might
    -1.09
     every
    -1.08
     should
    -1.03
     after
    -0.95
     may
    -0.91
     strong
    -0.91
     at
    -0.90
     reminiscent
    -0.89
    POSITIVE LOGITS
     modific
    1.37
    modified
    1.28
     modif
    1.27
     моди
    1.23
    combined
    1.21
     adapt
    1.18
     modi
    1.17
     modified
    1.17
     adapted
    1.14
     modifications
    1.13
    Activations Density 0.146%

    No Known Activations