© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57524
    Prev
    Next
    INDEX
    Explanations

    commands and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectors
    0.46
    Deposit
    0.40
    Hus
    0.40
     Deposit
    0.40
     TSP
    0.38
    ﺂ
    0.38
    Olivia
    0.37
     स्पी
    0.37
    MSS
    0.37
     modelBuilder
    0.37
    POSITIVE LOGITS
    iber
    0.43
    classList
    0.41
    (()
    0.39
    earic
    0.38
    ('../
    0.38
     alarm
    0.36
     worry
    0.35
     orgull
    0.35
    рень
    0.35
     valg
    0.35
    Activations Density 0.004%

    No Known Activations