© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13826
    Prev
    Next
    INDEX
    Explanations

    numbers and common separators

    np_acts-logits-general · gemini-2.5-flash-lite

    important considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     ifs
    0.46
    K
    0.44
    prism
    0.42
    につなが
    0.41
    Lab
    0.40
    ောက်ပ
    0.40
     pana
    0.40
     melawan
    0.39
     storied
    0.39
    og
    0.39
    POSITIVE LOGITS
     &/
    0.96
     (&
    0.72
     VERY
    0.62
     हेतु
    0.59
     تُ
    0.59
     &
    0.57
    क़्त
    0.56
    嗎
    0.56
     يُ
    0.55
     sooo
    0.55
    Activations Density 0.742%

    No Known Activations