© 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. 63008
    Prev
    Next
    INDEX
    Explanations

    ES, ARM, GPU, RT, OS, FTP

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

    The neuron fires on multi-letter uppercase abbreviations or acronyms (e.g. ES5, JS, ARM, GPU, etc.).

    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
     there
    -1.04
    じゃない
    -0.99
    R
    -0.90
    E
    -0.90
     obwohl
    -0.90
    値段
    -0.85
    P
    -0.81
    でない
    -0.79
     the
    -0.79
    二つ
    -0.79
    POSITIVE LOGITS
     køb
    0.95
     befolk
    0.92
    üstung
    0.91
    oté
    0.91
     perioden
    0.88
     ditt
    0.87
    isEmpty
    0.85
     annons
    0.85
    的话
    0.85
     bilan
    0.84
    Activations Density 0.156%

    No Known Activations