© 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. 90119
    Prev
    Next
    INDEX
    Explanations

    on management or out of

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

    efficiency related to 'instructions'

    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
     on
    0.48
    வம்
    0.46
    🧨
    0.46
    ﻓ
    0.44
    卄
    0.44
    <0x89>
    0.44
    าน
    0.44
    तंत्र
    0.44
     sains
    0.44
     mukaan
    0.43
    POSITIVE LOGITS
    {\
    0.39
     мировой
    0.38
    émi
    0.38
    ené
    0.38
    它们的
    0.37
    elje
    0.36
    zetek
    0.36
    ettamente
    0.36
    പ്പെടുന്ന
    0.36
    pak
    0.36
    Activations Density 0.004%

    No Known Activations