© 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-65K
    7. 55599
    Prev
    Next
    INDEX
    Explanations

    especially numbers

    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
    いて
    0.51
    름
    0.47
    ériment
    0.45
    மான
    0.44
    ၡ
    0.43
     fonctionnalité
    0.42
     xứng
    0.42
    するもの
    0.42
    лина
    0.41
    ត់
    0.41
    POSITIVE LOGITS
     torrential
    0.45
     مساء
    0.44
     rainfall
    0.43
     steaks
    0.43
     电
    0.43
     conferences
    0.42
     denitrification
    0.42
     countries
    0.41
     rains
    0.41
     comedians
    0.41
    Activations Density 0.001%

    No Known Activations