© 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. 92926
    Prev
    Next
    INDEX
    Explanations

    newly available

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

    The neuron detects tokens that announce or emphasize the release, publication, or availability of something (e.g. “released,” “published,” “available,” “launched,” “arrived,” “out now,” 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_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
    _
    -1.52
     \
    -1.41
     &
    -1.37
    }\
    -1.36
     \\
    -1.34
    a
    -1.34
    or
    -1.31
    ac
    -1.28
    u
    -1.27
     who
    -1.23
    POSITIVE LOGITS
     rése
    1.55
     vernis
    1.37
     remé
    1.27
     pán
    1.26
     coussin
    1.25
     bús
    1.25
     ideje
    1.23
     MÁ
    1.22
    猹
    1.20
    manı
    1.18
    Activations Density 0.080%

    No Known Activations