© 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. 22-GEMMASCOPE-RES-131K
    7. 13935
    Prev
    Next
    INDEX
    Explanations

    product numbers and identifiers

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

    The neuron flags tokens that are part of luxury item model names and edition labels (e.g. “Limited,” “Edition,” “Mirage,” “Speedy,” and their variant numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    liun
    -1.13
    をご覧ください
    -1.06
    を見ると
    -1.03
     निम्न
    -1.02
    を見ながら
    -1.00
     aquarelle
    -0.99
    gameserver
    -0.99
    rowe
    -0.99
    ଶ
    -0.99
    zumaki
    -0.98
    POSITIVE LOGITS
    Beskrivelse
    1.40
    ينج
    1.34
    توضیحات
    1.33
    Beskrivning
    1.28
    Kondisi
    1.26
    私が
    1.25
    Jenis
    1.23
    نحوه
    1.23
    Kuva
    1.21
    Hanya
    1.21
    Activations Density 0.000%

    No Known Activations