© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25585
    Prev
    Next
    INDEX
    Explanations

    positive qualities or assessments

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

    This neuron detects positive evaluative adjectives (e.g., good, great, best, excellent) used to praise or promote something.

    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
     koste
    -0.93
     cewek
    -0.91
     vekt
    -0.90
     ekst
    -0.86
    shutterstock
    -0.85
     koke
    -0.84
     kalori
    -0.84
     leveren
    -0.84
    Shutterstock
    -0.83
    ፨
    -0.81
    POSITIVE LOGITS
     performance
    1.06
    PhysRev
    1.05
     conditions
    1.05
     choice
    1.04
     results
    1.02
     predisposition
    0.98
     relationship
    0.97
     combination
    0.95
     deal
    0.94
     mood
    0.92
    Activations Density 0.014%

    No Known Activations