© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112405
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "mind"

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

    The neuron activates on occurrences of the word “Mind” (especially as part of titles or named entities).

    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
    ↵
    -2.89
     
    -2.44
     ”
    -2.41
     beliebtesten
    -2.30
     vorigen
    -2.22
     jahr
    -2.19
     Kombination
    -2.17
    0
    -2.14
     geniş
    -2.14
    jenigen
    -2.14
    POSITIVE LOGITS
    泺
    2.55
    獁
    2.41
     expérience
    2.34
    illants
    2.34
    鄚
    2.33
     时尚
    2.27
    
    2.27
    ساخت
    2.25
     简约
    2.25
    lessly
    2.25
    Activations Density 0.006%

    No Known Activations