© 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. 69153
    Prev
    Next
    INDEX
    Explanations

    posting questions or effort

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

    This neuron detects user-directed moderation directives phrased as imperative requests—especially “don’t cross-post like this.”

    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
     with
    -1.09
     during
    -1.05
     among
    -0.94
    COOH
    -0.92
    rootView
    -0.89
     my
    -0.88
    ەر
    -0.87
     at
    -0.85
     I
    -0.84
    abilir
    -0.84
    POSITIVE LOGITS
     your
    1.52
     uſe
    1.15
     posting
    1.02
    ︲
    1.01
     takie
    1.01
    chó
    0.99
     you
    0.98
     pubblici
    0.97
     juſ
    0.96
    耵
    0.94
    Activations Density 0.078%

    No Known Activations