© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 128
    Prev
    Next
    INDEX
    Explanations

    maintaining trust and transparency

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     imati
    0.30
     attempting
    0.28
     Danger
    0.27
    Danger
    0.27
     Veamos
    0.27
    だが
    0.26
     اختر
    0.26
    [/
    0.26
     Allerdings
    0.26
     kebanyakan
    0.26
    POSITIVE LOGITS
     awareness
    0.80
    awareness
    0.70
     efficiencies
    0.58
     synergies
    0.55
     जागरूकता
    0.53
     empathy
    0.53
     inclusivity
    0.53
     transparency
    0.52
     partnerships
    0.52
     Awareness
    0.52
    Activations Density 0.923%

    No Known Activations