© 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. 54189
    Prev
    Next
    INDEX
    Explanations

    common phrases and names

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

    The neuron fires strongly on section titles, headings, and URLs—that is, on the text that marks out article or post titles (including embedded links).

    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
    💋
    -1.45
    ❔
    -1.39
    ☝
    -1.34
    Bibliografie
    -1.32
     mola
    -1.31
    🏟
    -1.30
    😲
    -1.30
    🤓
    -1.30
    ╰
    -1.29
    🤪
    -1.28
    POSITIVE LOGITS
     probablemente
    1.52
     talvez
    1.43
     którą
    1.41
     acredita
    1.40
     evrops
    1.38
     möchtest
    1.37
     maybe
    1.35
     things
    1.35
     lots
    1.34
     serán
    1.34
    Activations Density 0.083%

    No Known Activations