© 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. 15320
    Prev
    Next
    INDEX
    Explanations

    impossibly

    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
    டன்
    1.38
     Refs
    1.35
     unm
    1.35
     carico
    1.34
    apiUrl
    1.28
     dioxide
    1.28
    ᾖ
    1.26
    н
    1.26
     dezvolt
    1.26
    भवती
    1.26
    POSITIVE LOGITS
    ك
    1.60
    샵
    1.48
     माया
    1.46
    ந்தது
    1.46
     sorption
    1.43
    land
    1.41
    导致
    1.39
     πάν
    1.37
    膣
    1.36
     분
    1.36
    Activations Density 0.001%

    No Known Activations