© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68428
    Prev
    Next
    INDEX
    Explanations

    game, costume, available

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

    The neuron fires on prominent content words in headings or titles (e.g. product or section names).

    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
    にします
    -1.50
    為に
    -1.45
    ところに
    -1.17
    ためには
    -1.16
    ことも
    -1.16
    んですよね
    -1.15
    ございました
    -1.11
    からお
    -1.11
     something
    -1.10
     ripet
    -1.10
    POSITIVE LOGITS
     is
    2.44
    は
    1.74
    を
    1.45
     was
    1.43
    但却
    1.38
     will
    1.32
     may
    1.30
    ですが
    1.28
     comenzará
    1.28
     has
    1.27
    Activations Density 0.000%

    No Known Activations