© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5406
    Prev
    Next
    INDEX
    Explanations

    pain, soreness, joints

    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_13_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
     lifestyles
    2.28
     Iya
    2.12
    ೋತಿ
    2.10
     оди
    2.08
    ﯼ
    2.02
     おり
    2.01
     incomes
    2.00
    浒
    1.97
    aternary
    1.96
     NICKEL
    1.93
    POSITIVE LOGITS
    u
    2.40
    ל
    2.12
    न
    2.01
    ceme
    1.96
    c
    1.92
    ल
    1.81
    a
    1.80
    hain
    1.80
    killer
    1.79
    aul
    1.78
    Activations Density 0.951%

    No Known Activations