© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35624
    Prev
    Next
    INDEX
    Explanations

    patients with medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    launch, ceremony, reduce, man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Adin
    0.52
    峤
    0.46
     sient
    0.45
    心的
    0.44
     sluč
    0.43
    Rl
    0.43
    けれ
    0.42
    చేసిన
    0.41
     Donation
    0.41
     Heartland
    0.41
    POSITIVE LOGITS
    0.61
     launch
    0.49
     запуска
    0.49
     launches
    0.46
     require
    0.45
     velocidad
    0.45
    י
    0.44
    Г
    0.43
     लॉन्च
    0.42
     any
    0.42
    Activations Density 0.000%

    No Known Activations