© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7723
    Prev
    Next
    INDEX
    Explanations

    Gan Fink Gib Gin doctor lim

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

    GPT and GD prefixes

    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_53_width_65k_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
    জনক
    0.42
    ⚌
    0.40
    水素
    0.40
     subgroups
    0.37
    
    0.36
     Бекер
    0.35
    慗
    0.35
    ᠬ
    0.35
    Ŏ
    0.34
    稷
    0.34
    POSITIVE LOGITS
     GV
    2.19
     GS
    2.11
     GD
    2.09
     GW
    2.06
     GF
    2.03
     GK
    2.03
     GC
    2.02
     GX
    2.02
     GP
    1.98
     GB
    1.95
    Activations Density 0.563%

    No Known Activations