© 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. 70
    Prev
    Next
    INDEX
    Explanations

    emojis and positive sentiment

    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
     t
    0.58
     T
    0.58
     w
    0.53
     c
    0.52
     character
    0.52
    emic
    0.50
    iggers
    0.49
     secret
    0.48
     restricts
    0.47
     called
    0.45
    POSITIVE LOGITS
    <end_of_turn>
    1.98
    希望
    1.14
    Hope
    1.05
    hope
    1.03
    Additionally
    1.01
    Hopefully
    0.99
    Furthermore
    0.98
    Enjoy
    0.98
    Finally
    0.98
    Remember
    0.98
    Activations Density 2.943%

    No Known Activations