© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14049
    Prev
    Next
    INDEX
    Explanations

    What is X?

    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
     MLAs
    1.10
    တတ်
    1.07
    𝗍
    1.06
    痧
    1.06
     glycoproteins
    1.04
     clientes
    1.04
    𝖽
    1.04
    MACl
    1.03
     emailing
    1.02
     taala
    1.00
    POSITIVE LOGITS
     /
    0.65
     biography
    0.63
     Summary
    0.58
     (
    0.55
     key
    0.55
     description
    0.54
     Tou
    0.53
     Description
    0.52
     [
    0.52
     Im
    0.52
    Activations Density 0.031%

    No Known Activations