© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32911
    Prev
    Next
    INDEX
    Explanations

    UI capabilities and interactions

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

    The neuron fires on JavaScript object property names (config option keys) in code.

    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
     agus
    -1.16
    檚
    -1.03
    xampp
    -0.98
     to
    -0.94
     serce
    -0.93
    ჟ
    -0.92
    Semitism
    -0.90
    NameIn
    -0.90
     our
    -0.89
    }$_
    -0.89
    POSITIVE LOGITS
     можли
    1.23
    允许
    1.17
    Allowed
    1.16
     ability
    1.14
     única
    1.13
     allowed
    1.13
    פשר
    1.12
    許
    1.09
     permitted
    1.05
     Freitas
    1.03
    Activations Density 0.016%

    No Known Activations