© 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. 10-GEMMASCOPE-RES-131K
    7. 20798
    Prev
    Next
    INDEX
    Explanations

    saying reviews testimonials

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

    The neuron detects headings or labels for customer‐ or user‐generated reviews and testimonials (e.g. “What people are saying,” “Our students say,” “Testimonials,” “Press reviews,” 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
     to
    -1.79
     However
    -1.78
     Because
    -1.67
    However
    -1.47
     What
    -1.44
     Why
    -1.44
     also
    -1.39
     Also
    -1.38
     It
    -1.37
     This
    -1.34
    POSITIVE LOGITS
     such
    1.93
     églises
    1.44
    动静
    1.39
    ことなく
    1.34
    ⠀⠀⠀⠀
    1.27
     herbes
    1.25
    ことがある
    1.24
     recenti
    1.23
     SUCH
    1.22
     semblent
    1.22
    Activations Density 0.034%

    No Known Activations