© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4900
    Prev
    Next
    INDEX
    Explanations

    absence of something

    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_17_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
     nicknamed
    0.79
     explaining
    0.75
    绀
    0.65
     normalen
    0.65
     hoped
    0.64
    ện
    0.64
    嚮
    0.64
    öh
    0.62
     spinach
    0.61
     않고
    0.61
    POSITIVE LOGITS
    fus
    0.86
     Finished
    0.85
     Finale
    0.85
     চাহ
    0.82
     행
    0.81
    ratio
    0.81
     পূর্ণ
    0.80
    宄
    0.80
     actuaciones
    0.78
    equalsIgnoreCase
    0.77
    Activations Density 0.016%

    No Known Activations