© 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. 9409
    Prev
    Next
    INDEX
    Explanations

    property assignment

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

    The neuron activates on object member names accessed via dot notation in code (i.e. property or method identifiers following “.”).

    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
    蛱
    -1.48
     their
    -1.44
     maravilh
    -1.41
    från
    -1.41
     they
    -1.41
    镲
    -1.40
     into
    -1.37
     them
    -1.30
    believe
    -1.29
     espet
    -1.29
    POSITIVE LOGITS
     was
    1.53
     =
    1.48
     is
    1.48
    は
    1.38
     had
    1.33
    錨
    1.32
    Dettagli
    1.21
    ！！！！
    1.20
    饗
    1.20
    hyth
    1.19
    Activations Density 0.012%

    No Known Activations