© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102852
    Prev
    Next
    INDEX
    Explanations

    CRUD actions or data controllers

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

    The neuron strongly activates on code identifiers—especially class names and method/action names (like Create, Model, view, update, show, edit)—in programming snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    mainly
    -1.28
    idk
    -1.00
    probably
    -0.94
     исчез
    -0.94
    ys
    -0.93
     evtl
    -0.93
    possibly
    -0.92
     apoio
    -0.92
    ומות
    -0.92
    ink
    -0.92
    POSITIVE LOGITS
    Many
    1.31
    Despite
    1.19
    Every
    1.19
     one
    1.15
     as
    1.13
    Other
    1.11
    Even
    1.09
    אני
    1.09
     from
    1.08
    All
    1.06
    Activations Density 0.016%

    No Known Activations