© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3419
    Prev
    Next
    INDEX
    Explanations

    year and annual time references

    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_16_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
    ي
    1.26
    t
    1.16
    i
    1.13
    ಿ
    1.05
     suono
    0.99
     romanzo
    0.98
     testicule
    0.95
    جے
    0.95
     разработ
    0.94
    ി
    0.94
    POSITIVE LOGITS
    EL
    1.42
    O
    1.34
    OS
    1.30
    ID
    1.29
    IT
    1.25
    PS
    1.23
    Year
    1.23
    ET
    1.21
    OP
    1.21
    U
    1.20
    Activations Density 0.136%

    No Known Activations