© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    for example

    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
     Thank
    0.98
    Thank
    0.92
     Untuk
    0.81
     untuk
    0.81
     hãy
    0.80
     Also
    0.80
    とも
    0.79
    也
    0.78
     with
    0.78
     for
    0.77
    POSITIVE LOGITS
     example
    1.28
     instance
    1.20
     sure
    1.13
     each
    1.11
    instance
    1.08
    ked
    1.07
    geries
    1.06
     purposes
    1.06
     now
    1.03
     ejemplo
    1.01
    Activations Density 0.698%

    No Known Activations