© 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. 152469
    Prev
    Next
    INDEX
    Explanations

    topics that follow specific words

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

    response letter or table

    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
    ロット
    0.46
     LOT
    0.45
     Byron
    0.45
     Byzantine
    0.44
    л
    0.44
     requirement
    0.44
     RMB
    0.44
     입장
    0.44
     supernova
    0.44
     Roth
    0.43
    POSITIVE LOGITS
    réd
    0.52
    mot
    0.51
    ArchivePath
    0.50
    uanya
    0.49
     പഞ്ചായ
    0.49
    conexion
    0.49
    b
    0.49
    Metric
    0.48
    puede
    0.48
    pendiente
    0.48
    Activations Density 0.000%

    No Known Activations