© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10633
    Prev
    Next
    INDEX
    Explanations

    for the following word

    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_65k_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
     друг
    0.41
     இருப்ப
    0.36
    딪
    0.36
     bookmarks
    0.36
    )=
    0.35
    keepers
    0.35
     reconocer
    0.35
    .*\
    0.35
    ﺝ
    0.35
     सोमवार
    0.35
    POSITIVE LOGITS
     eftersom
    0.44
     параметра
    0.42
     вместо
    0.41
    にあ
    0.40
     penalty
    0.39
     prä
    0.39
     beneficiary
    0.38
     Bewertung
    0.38
     معیار
    0.38
     évaluation
    0.38
    Activations Density 0.077%

    No Known Activations