© 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. 10-GEMMASCOPE-RES-131K
    7. 3684
    Prev
    Next
    INDEX
    Explanations

    supernatural, paranormal, occult themes

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

    The neuron detects words referring to supernatural, occult, or paranormal phenomena.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    釭
    -2.80
    赑
    -2.66
    ໊
    -2.59
    簠
    -2.36
    ৢ
    -2.25
    鬭
    -2.25
    м
    -2.19
    同じく
    -2.17
    蟊
    -2.16
    枥
    -2.14
    POSITIVE LOGITS
    “
    3.59
    The
    2.78
     “(
    2.34
    ↵↵
    2.31
    }
    2.27
    H
    2.16
    ”
    2.14
    <i>
    2.08
    他
    2.06
    <sup>
    2.05
    Activations Density 0.005%

    No Known Activations