© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12438
    Prev
    Next
    INDEX
    Explanations

    current or is

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

    The neuron is looking for highly subjective, sentiment-laden words (strong opinionated adjectives or adverbs) that convey personal judgments or emotional emphasis.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    1.33
    http
    1.23
    －－
    0.93
    
    0.92
    Incidentally
    0.91
    StringBuffer
    0.91
    Television
    0.88
    Graphics
    0.86
    Telephone
    0.86
     http
    0.84
    POSITIVE LOGITS
    🫠
    1.88
    🫡
    1.87
    🥹
    1.80
    🫶
    1.77
     impactful
    1.70
    🥲
    1.70
     covid
    1.67
     onboarding
    1.66
     fintech
    1.63
     metaverse
    1.62
    Activations Density 0.056%

    No Known Activations