© 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. 34-GEMMASCOPE-RES-131K
    7. 82605
    Prev
    Next
    INDEX
    Explanations

    making things easier

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

    This neuron fires on marketing‐style hyperbole, especially the “has never been so <adjective>” phrasing.

    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
    inally
    -0.99
    paa
    -0.90
     magis
    -0.88
    ELESS
    -0.88
    jacking
    -0.87
    agerie
    -0.87
     彼女
    -0.85
     kuda
    -0.85
    ✺
    -0.84
    .)}
    -0.83
    POSITIVE LOGITS
     easy
    5.94
     easier
    5.06
    easy
    4.31
     fácil
    3.91
     Easy
    3.77
    Easy
    3.59
     EASY
    3.58
    easier
    3.53
     easiest
    3.47
     dễ
    3.31
    Activations Density 0.101%

    No Known Activations