© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5218
    Prev
    Next
    INDEX
    Explanations

    sleep quality and routine

    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
    龚
    0.81
     mustard
    0.80
     Palladium
    0.80
     groupBox
    0.77
     Truss
    0.77
     गोला
    0.77
    钮
    0.76
     Mich
    0.74
    肨
    0.74
     Mustard
    0.74
    POSITIVE LOGITS
     sleep
    2.12
     Sleep
    2.02
    Sleep
    2.00
    sleep
    1.76
     sleeping
    1.69
    睡眠
    1.63
     slept
    1.59
     Schlaf
    1.59
     Sleeping
    1.58
     asleep
    1.56
    Activations Density 0.270%

    No Known Activations