© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14659
    Prev
    Next
    INDEX
    Explanations

    technical terms and facts

    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_13_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
     Ende
    0.95
     Think
    0.94
     think
    0.92
    Think
    0.92
     bien
    0.87
    ть
    0.87
    o
    0.87
    sted
    0.86
    е
    0.86
     thoughtful
    0.86
    POSITIVE LOGITS
     anharmonic
    1.13
    䔀
    1.08
    :‏
    1.08
    फाइनल
    1.07
     biogas
    1.05
     ladle
    1.05
    ipine
    1.05
    箩
    1.04
     spiega
    1.03
     população
    1.03
    Activations Density 0.000%

    No Known Activations