© 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. 31-GEMMASCOPE-2-RES-262K
    7. 11428
    Prev
    Next
    INDEX
    Explanations

    sections with headings

    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_31_width_262k_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
     Entonces
    0.28
    これは
    0.28
    ט
    0.27
     написа
    0.26
    어
    0.26
     사랑
    0.25
    あなた
    0.25
    詩
    0.24
     όχι
    0.24
    문
    0.24
    POSITIVE LOGITS
     networked
    0.24
    IOD
    0.22
     streamlines
    0.22
     loaders
    0.22
    cmp
    0.21
     radios
    0.21
     cleats
    0.21
     competitively
    0.20
    ‌ర
    0.20
     inserts
    0.20
    Activations Density 0.030%

    No Known Activations