© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12706
    Prev
    Next
    INDEX
    Explanations

    language specific assistance

    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
    lipidemia
    1.44
     Costco
    1.44
     discretion
    1.35
    /-
    1.33
    ोत्तम
    1.30
     utilization
    1.28
    %/
    1.28
    レクト
    1.24
     interchangeably
    1.22
    वाधिकार
    1.21
    POSITIVE LOGITS
    ğa
    1.73
    ilver
    1.63
    рях
    1.61
    мут
    1.55
    üng
    1.54
    рес
    1.51
    flug
    1.51
    𝚑
    1.49
    üst
    1.48
     nád
    1.46
    Activations Density 0.000%

    No Known Activations