© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7918
    Prev
    Next
    INDEX
    Explanations

    latex math equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    preceq
    1.65
    Ü
    1.64
    Ş
    1.64
    Ğ
    1.63
    Ö
    1.62
    ﻬ
    1.59
    ANK
    1.58
    व्यक्तित्व
    1.58
    Ps
    1.56
    ﭜ
    1.55
    POSITIVE LOGITS
     clin
    1.44
     pop
    1.36
     often
    1.35
     application
    1.32
     бы
    1.30
     alto
    1.28
    bells
    1.28
     cube
    1.25
     operating
    1.25
     apt
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.