© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6288
    Prev
    Next
    INDEX
    Explanations

    equations with powers of x

    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
    דר
    0.43
    ্যাটে
    0.41
    ULTURE
    0.40
    טו
    0.39
     MAT
    0.39
    ்கலை
    0.39
     Biochem
    0.39
    摖
    0.39
    锶
    0.39
    ORTH
    0.38
    POSITIVE LOGITS
     esta
    0.39
     hennes
    0.39
     f
    0.38
     seu
    0.38
     this
    0.38
     Rumah
    0.38
     sufficient
    0.37
     are
    0.37
     oleh
    0.37
     هنا
    0.37
    Activations Density 0.007%

    No Known Activations