© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102647
    Prev
    Next
    INDEX
    Explanations

    favorite categories of things

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

    The neuron detects mentions of personal “favorites,” i.e. occurrences of “favorite” (or related) paired with the noun of the item being liked.

    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
     \
    -1.37
    ಏ
    -1.22
     \&
    -1.20
     її
    -1.16
    </th>
    -1.15
    жели
    -1.14
     integrante
    -1.13
     what
    -1.13
    ≦
    -1.11
     judul
    -1.10
    POSITIVE LOGITS
     Depois
    1.42
     favourites
    1.36
     AUSSI
    1.27
     favorites
    1.27
     rea
    1.26
     Enquanto
    1.23
     Também
    1.23
     cun
    1.23
    ptăm
    1.21
    啬
    1.21
    Activations Density 0.028%

    No Known Activations