© 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. 34-GEMMASCOPE-RES-131K
    7. 77968
    Prev
    Next
    INDEX
    Explanations

    programming snippets, code, licenses

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

    The neuron fires on occurrences of restrictive qualifier language—especially the word “only” and its surrounding “only X” or “only if X” constructions that set exclusive conditions.

    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
     just
    -1.20
     просто
    -0.91
     einfach
    -0.89
    Просто
    -0.87
    padek
    -0.80
     crafty
    -0.79
     gewoon
    -0.78
    埤
    -0.77
     simplemente
    -0.75
    🧱
    -0.75
    POSITIVE LOGITS
    ">+
    0.89
     dotenv
    0.85
    ">'.$
    0.85
    лона
    0.85
    zid
    0.84
     kebun
    0.78
     adev
    0.77
    uparrow
    0.76
    coordinate
    0.75
    dsa
    0.75
    Activations Density 0.074%

    No Known Activations