© 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. 31-GEMMASCOPE-2-RES-262K
    7. 111922
    Prev
    Next
    INDEX
    Explanations

    artificial quartz, grant goods, steps until

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

    multiple, several, or many

    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_31_width_262k_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
     tracers
    0.46
    yi
    0.45
     issuers
    0.45
     Funcion
    0.44
     borrowers
    0.43
     Yue
    0.43
     Hui
    0.42
    譙
    0.42
     Borrower
    0.42
     flutter
    0.42
    POSITIVE LOGITS
    成品
    0.49
     bepaalde
    0.48
     ascension
    0.46
    Several
    0.45
    複数
    0.45
     вернуть
    0.44
     природных
    0.44
     Enzymes
    0.43
     озе
    0.43
     zdecyd
    0.42
    Activations Density 0.000%

    No Known Activations