© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137619
    Prev
    Next
    INDEX
    Explanations

    Rayleigh scattering, VStack, flares

    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
    ন
    0.48
    तियों
    0.46
    ajā
    0.45
    ܡܪ
    0.44
    𝑐
    0.44
    صوص
    0.44
    ্সা
    0.44
     inefficiencies
    0.44
     Parton
    0.43
    𝐊
    0.42
    POSITIVE LOGITS
     सुन
    0.40
     clade
    0.39
     valentine
    0.38
     входит
    0.38
     начинает
    0.38
    พ
    0.38
    暐
    0.38
     Azores
    0.37
     язы
    0.37
     zullen
    0.37
    Activations Density 0.003%

    No Known Activations