© 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. 34-GEMMASCOPE-RES-131K
    7. 103729
    Prev
    Next
    INDEX
    Explanations

    Nick Saban

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

    The neuron fires on programming‐style identifiers (e.g. attribute or property names like “name,” “keyboardType,” “align,” “height,” etc.) rather than ordinary English words.

    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
    能否
    -0.82
     which
    -0.75
    ligen
    -0.73
    opress
    -0.72
     लेकर
    -0.72
     sintomi
    -0.72
     UserRepository
    -0.71
    ừ
    -0.71
     akik
    -0.71
     getConnection
    -0.70
    POSITIVE LOGITS
     alignments
    0.84
    Sail
    0.84
    however
    0.82
    varande
    0.82
    iras
    0.81
     первую
    0.81
     Covering
    0.81
     jub
    0.80
    ,
    0.78
    alignment
    0.78
    Activations Density 0.000%

    No Known Activations