© 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. 15528
    Prev
    Next
    INDEX
    Explanations

    C# using directives

    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
    🫰
    0.48
     làn
    0.46
     ৫৭
    0.45
    🫠
    0.45
    排列
    0.43
    🫦
    0.43
    梸
    0.42
    🥹
    0.42
    দুই
    0.42
    🫣
    0.42
    POSITIVE LOGITS
     Festa
    0.51
    Grad
    0.41
     Feast
    0.41
     Wolf
    0.40
     Veterinary
    0.39
    OCS
    0.39
     Grad
    0.38
     Beck
    0.38
     Graduation
    0.38
    UnitTest
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.