© 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. 223883
    Prev
    Next
    INDEX
    Explanations

    executive housekeeping

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

    Vibe Check: replica, harvest, MSA

    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
     অর্
    0.48
    Methylsulfanyl
    0.48
     gelişt
    0.46
     THAN
    0.45
    ukum
    0.44
    廰
    0.44
     develops
    0.43
    SHORT
    0.42
     الول
    0.41
     หัว
    0.41
    POSITIVE LOGITS
    Н
    0.52
     ruido
    0.48
    د
    0.48
     cerrado
    0.48
    涀
    0.48
    торов
    0.48
    டிப்ப
    0.46
    荸
    0.45
    バード
    0.44
    विण्यासाठी
    0.44
    Activations Density 0.000%

    No Known Activations