© 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. 34-GEMMASCOPE-RES-131K
    7. 106706
    Prev
    Next
    INDEX
    Explanations

    living better and happier

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

    The neuron fires most strongly on words that are part of enumerations or lists (e.g. items joined by commas and conjunctions like “and”/“or”).

    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
     жизнь
    -1.02
     زندگی
    -0.94
     siècles
    -0.92
    ジュース
    -0.91
    └──
    -0.88
     حياة
    -0.85
     життя
    -0.85
     tournage
    -0.84
    nemone
    -0.84
    ulus
    -0.84
    POSITIVE LOGITS
     relationships
    1.58
     exercise
    1.36
     hobby
    1.28
     hobbies
    1.26
     creative
    1.25
     friends
    1.22
     spiritual
    1.21
     health
    1.20
     physical
    1.20
     healthy
    1.18
    Activations Density 0.044%

    No Known Activations