© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    representations and where

    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
    िप्स
    1.16
     symptom
    1.04
    රක
    1.04
     PLIST
    1.03
     FC
    1.01
    🏃
    1.01
     장애
    1.00
    жется
    1.00
    versation
    0.99
     verb
    0.98
    POSITIVE LOGITS
    ،
    0.99
     بال
    0.97
     เพราะ
    0.93
     ان
    0.85
     piuttosto
    0.84
     من
    0.83
     وتح
    0.83
     وت
    0.82
     Insulation
    0.82
     وال
    0.81
    Activations Density 0.000%

    No Known Activations