© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4329
    Prev
    Next
    INDEX
    Explanations

    no events or empty

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

    The neuron flags phrases indicating “nothing to show” or “not found” states—i.e. empty‐or‐missing resource/error messages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    removeFrom
    -0.75
     ignore
    -0.75
    で使用
    -0.72
    dą
    -0.72
     GNP
    -0.71
     graças
    -0.69
    versiti
    -0.69
     Ignore
    -0.69
     tiktok
    -0.69
    間違い
    -0.69
    POSITIVE LOGITS
     empty
    1.99
     no
    1.98
    Empty
    1.89
    empty
    1.88
    ไม่มี
    1.87
    暂无
    1.84
     Empty
    1.73
     ไม่มี
    1.63
     there
    1.59
    EMPTY
    1.59
    Activations Density 0.011%

    No Known Activations