© 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. 95423
    Prev
    Next
    INDEX
    Explanations

    `final` objects

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

    The neuron fires on the keyword “final,” flagging declarations that use the final modifier.

    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
    ktion
    -1.20
    蟜
    -1.20
     dolay
    -1.13
     betere
    -1.13
     terse
    -1.11
     nombreuses
    -1.09
    了些
    -1.09
     bijna
    -1.08
    registrer
    -1.06
    了许多
    -1.06
    POSITIVE LOGITS
    However
    1.05
    也都
    0.96
    これからの
    0.94
    Then
    0.93
    a
    0.92
    在你
    0.90
    ,
    0.89
    ÍTULO
    0.89
     in
    0.88
     خالی
    0.85
    Activations Density 0.001%

    No Known Activations