© 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. 22-GEMMASCOPE-RES-131K
    4. 70818
    Prev
    Next
    INDEX
    Explanations

    API route definitions

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

    The neuron fires on square‐bracketed code annotations (e.g. “[HttpPost]”, “[ValidateInput(false)]”, “[Authorize]”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    малар
    -1.15
     GRATU
    -1.10
    ———
    -1.10
     puto
    -1.09
     ganda
    -1.09
     mily
    -1.05
     kuda
    -1.05
     bambu
    -1.05
     lucu
    -1.05
     Commentaires
    -1.05
    POSITIVE LOGITS
     at
    1.00
     )$
    0.96
     них
    0.88
     \,\
    0.88
     credence
    0.88
     rám
    0.86
     军
    0.85
     disintegration
    0.85
    phim
    0.85
     або
    0.84
    Activations Density 0.001%

    No Known Activations