© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95644
    Prev
    Next
    INDEX
    Explanations

    critique or warnings

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

    The neuron spikes on very common “high‐traffic” tokens—especially punctuation marks (e.g. periods and question marks) and frequent function words like “should,” “the,” 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_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
     requests
    -0.92
     boosts
    -0.92
    writeFileSync
    -0.88
     Selb
    -0.86
     assurances
    -0.86
     following
    -0.85
     замет
    -0.84
     disputes
    -0.84
     boost
    -0.83
     responses
    -0.83
    POSITIVE LOGITS
     Warnings
    0.93
     क्र
    0.91
     critique
    0.90
    haltung
    0.90
     систем
    0.85
    ūnas
    0.85
     dénon
    0.84
    آب
    0.84
     vernie
    0.84
    퓨
    0.84
    Activations Density 0.069%

    No Known Activations