© 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. 10-GEMMASCOPE-RES-131K
    7. 12488
    Prev
    Next
    INDEX
    Explanations

    Here's Why

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

    This neuron detects those click-bait or news-style headline lead-ins of the form “Here’s …” (e.g. “Here’s Why,” “Here’s What We Know,” “Here’s How,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     TRABAJO
    -1.44
     DÍA
    -1.41
    Ehh
    -1.37
    妩
    -1.31
    Wut
    -1.30
    Transk
    -1.29
    Kontra
    -1.23
     CONCEP
    -1.22
    的時候
    -1.21
    慫
    -1.21
    POSITIVE LOGITS
     instead
    1.48
     they
    1.23
     beliebtesten
    1.19
    bootstrapcdn
    1.19
    fois
    1.18
     confronto
    1.16
    哧
    1.16
     mici
    1.15
    ricing
    1.13
    いましたが
    1.11
    Activations Density 0.101%

    No Known Activations