© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8028
    Prev
    Next
    INDEX
    Explanations

    commenting on code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    <0x0D>
    0.44
     Пер
    0.43
     https
    0.43
     Replace
    0.43
    its
    0.41
     Find
    0.40
     Für
    0.40
    광
    0.39
    www
    0.38
     www
    0.38
    POSITIVE LOGITS
     problemen
    0.55
    τηση
    0.50
     problémy
    0.50
     problèmes
    0.48
     sorun
    0.48
     konfl
    0.47
    😣
    0.47
     problemi
    0.47
    arently
    0.47
     mlijeka
    0.47
    Activations Density 0.310%

    No Known Activations