© 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. 10674
    Prev
    Next
    INDEX
    Explanations

    listing online information

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

    The neuron strongly activates on title‐ or headline‐style marketing and navigation keywords (e.g. “Reviews,” “Analysis,” “Cheapest,” “Price,” “Watch…HD,” “For Sale & For Rent,” 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
    私の
    -1.36
    毎週
    -1.32
    ２
    -1.28
    自分の
    -1.23
     даже
    -1.20
    ۹
    -1.20
    6
    -1.19
    ４
    -1.16
    ۲
    -1.15
    Synonymes
    -1.14
    POSITIVE LOGITS
     now
    1.34
     how
    1.29
     today
    1.23
     here
    1.19
     who
    1.18
     is
    1.16
    pagnes
    1.13
    ایب
    1.13
     she
    1.12
    懸命
    1.12
    Activations Density 0.111%

    No Known Activations