© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3023
    Prev
    Next
    INDEX
    Explanations

    constantly learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frosts
    0.78
     Glacier
    0.68
     frost
    0.68
     Coney
    0.67
     газета
    0.66
     Gala
    0.65
     bullpen
    0.64
    氷
    0.61
     glaciers
    0.61
     Clinic
    0.61
    POSITIVE LOGITS
     learning
    2.71
     Learning
    2.56
    Learning
    2.53
    learning
    2.52
     learn
    2.28
     educational
    2.17
     learns
    2.17
     education
    2.16
     aprendizaje
    2.14
    learn
    2.12
    Activations Density 0.997%

    No Known Activations