© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8488
    Prev
    Next
    INDEX
    Explanations

    questions starting with what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     Carleton
    1.26
     Roulette
    1.16
     Blunt
    1.15
     Osiris
    1.14
     RPG
    1.12
     Vegas
    1.11
    吉
    1.11
     吉
    1.09
     Caesars
    1.09
     Tash
    1.05
    POSITIVE LOGITS
     milk
    2.89
     Milk
    2.79
    Milk
    2.69
    milk
    2.69
     MILK
    2.62
     mammary
    2.49
    乳
    2.45
     breastfeeding
    2.41
     breast
    2.40
     milking
    2.37
    Activations Density 0.337%

    No Known Activations