© 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. 82717
    Prev
    Next
    INDEX
    Explanations

    heavenly concepts and figures

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

    The neuron responds strongly to occurrences of the word “heaven” (and its variants like “heavenly” or “heavens”).

    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
     Indones
    -0.85
    ሌ
    -0.84
     presiden
    -0.84
     hijab
    -0.83
     proposito
    -0.82
    ündigt
    -0.81
     フロア
    -0.81
    ޫ
    -0.81
     dino
    -0.79
    Verbal
    -0.76
    POSITIVE LOGITS
     above
    1.52
    above
    1.45
    bove
    1.11
    выше
    1.09
     powy
    1.09
    Above
    1.05
     Above
    1.05
     gates
    1.05
     forbid
    1.04
     天
    1.03
    Activations Density 0.007%

    No Known Activations