© 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. 6409
    Prev
    Next
    INDEX
    Explanations

    core principles

    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
     dotyczące
    0.65
    后果
    0.62
    |");
    0.60
    atang
    0.58
     دخ
    0.58
     kıs
    0.58
    häng
    0.57
    াজ
    0.57
    °;
    0.57
     مربوط
    0.57
    POSITIVE LOGITS
     principles
    1.04
     principes
    0.99
     core
    0.99
     spirit
    0.99
    spirit
    0.99
     premise
    0.98
     Principles
    0.97
     Core
    0.94
    core
    0.90
     ideals
    0.87
    Activations Density 0.704%

    No Known Activations