© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58436
    Prev
    Next
    INDEX
    Explanations

    This is a definition

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

    The neuron fires on the common “This is…” phrase at the start of code comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ut
    -1.61
    ちゃんが
    -1.51
    >
    -1.44
     informacion
    -1.41
    じゃなくて
    -1.40
    不僅
    -1.37
    日を
    -1.36
     ilha
    -1.32
     delicioso
    -1.31
    してない
    -1.31
    POSITIVE LOGITS
    ’
    1.90
     to
    1.50
    though
    1.48
     like
    1.44
    стями
    1.41
    '
    1.36
    kanak
    1.31
     Το
    1.27
    ERMIN
    1.27
    stoy
    1.27
    Activations Density 0.116%

    No Known Activations