© 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. 5818
    Prev
    Next
    INDEX
    Explanations

    explains specific places, programs, or entities

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

    separate concerns

    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
    ıc
    0.38
    メガネ
    0.35
    那位
    0.33
    幼儿园
    0.33
    ्यूटर
    0.32
    ѵ
    0.31
    ▇
    0.31
    あた
    0.31
    aterina
    0.31
    isons
    0.31
    POSITIVE LOGITS
     КС
    1.02
     FF
    0.95
     FS
    0.91
     SJ
    0.91
     TS
    0.91
     MW
    0.91
     MB
    0.90
     CC
    0.90
     KS
    0.89
     SZ
    0.89
    Activations Density 0.745%

    No Known Activations