© 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. 40-GEMMASCOPE-2-RES-65K
    7. 54650
    Prev
    Next
    INDEX
    Explanations

    code comments and numbers

    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/layer_40_width_65k_l0_medium
    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
    وما
    0.38
    𝐋
    0.38
     Preface
    0.36
     яго
    0.36
    繕
    0.35
    TIM
    0.35
    ریشن
    0.35
     Й
    0.34
    Cu
    0.34
     мето
    0.33
    POSITIVE LOGITS
    memset
    0.48
     reset
    0.47
    reset
    0.45
    zero
    0.42
     zero
    0.42
     wieder
    0.39
     ફરી
    0.39
     አበባ
    0.38
     igen
    0.38
     ones
    0.37
    Activations Density 0.075%

    No Known Activations