© 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. 36612
    Prev
    Next
    INDEX
    Explanations

    reasons it happens

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

    The neuron strongly activates on flashy, promotional or sensational language—e.g. emphatic ad copy, click-baity intensifiers, and attention-grabbing phrases.

    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
     all
    -1.12
     from
    -1.02
     націона
    -1.00
    ּוֹ
    -0.96
     in
    -0.94
     at
    -0.92
     on
    -0.92
    וּ
    -0.92
     those
    -0.91
    XCTAssertEqual
    -0.91
    POSITIVE LOGITS
     chinos
    1.18
     беже
    1.17
     soigneusement
    1.15
    ILAR
    1.13
     perpétu
    1.13
     Eſ
    1.13
     chré
    1.13
     درباره
    1.10
    begingroup
    1.08
     régl
    1.08
    Activations Density 0.041%

    No Known Activations