© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42633
    Prev
    Next
    INDEX
    Explanations

    Tanner followed by noun

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

    The neuron fires on capitalized proper names and titles (e.g. personal names, lecture series names, gallery names, and other named entities).

    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
     تحتاج
    -2.56
     {
    -2.48
     Pemer
    -2.39
     catapult
    -2.34
    鑁
    -2.30
     unsurpassed
    -2.28
    疍
    -2.28
     Membuat
    -2.27
    樒
    -2.16
    çok
    -2.13
    POSITIVE LOGITS
    .
    2.89
     were
    2.56
     -
    2.45
    <i>
    2.33
    which
    2.28
     THE
    2.20
    </td>
    2.17
    D
    2.16
    </h1>
    2.13
    ?
    2.08
    Activations Density 0.002%

    No Known Activations