© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73220
    Prev
    Next
    INDEX
    Explanations

    IL Assembly, IL-12, IL App, IL Controller

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

    The neuron is triggered by occurrences of “IL” (Intermediate Language) identifiers in code or metadata contexts.

    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
     with
    -2.14
     for
    -2.09
     and
    -2.08
    e
    -1.86
    );
    -1.85
     or
    -1.85
    f
    -1.84
    i
    -1.70
     including
    -1.69
     from
    -1.68
    POSITIVE LOGITS
    ujem
    1.71
    donde
    1.70
     Quando
    1.69
    requestCode
    1.62
    坶
    1.60
    Mvh
    1.59
     disponibili
    1.59
    probieren
    1.58
     SINCE
    1.52
    ZIONI
    1.52
    Activations Density 0.000%

    No Known Activations