© 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. 41007
    Prev
    Next
    INDEX
    Explanations

    large numbers and percentages

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

    start now

    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
     nef
    0.41
     precipitation
    0.40
     supra
    0.39
    顰
    0.38
    粒
    0.38
     peculiarities
    0.38
     measured
    0.37
     seismic
    0.37
    )\|_{
    0.37
     unspecified
    0.37
    POSITIVE LOGITS
    酆
    0.64
    澳门
    0.52
    Ặ
    0.45
    शुल्क
    0.44
     solvers
    0.44
     މަ
    0.44
    콴
    0.44
    用来
    0.43
    entraî
    0.43
    фициа
    0.43
    Activations Density 0.000%

    No Known Activations