© 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. 83825
    Prev
    Next
    INDEX
    Explanations

    months and examples

    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
     và
    0.47
     chỉ
    0.47
     и
    0.46
     গেলে
    0.43
     чем
    0.43
    能够
    0.43
     necesitamos
    0.42
    的数量
    0.42
    ফি
    0.42
     Aviation
    0.41
    POSITIVE LOGITS
    幸せ
    0.49
     automorphisms
    0.48
     anses
    0.48
     peasantry
    0.47
     automorphism
    0.46
     obsolete
    0.45
     incriminating
    0.44
     α
    0.43
    慚
    0.43
     blemishes
    0.43
    Activations Density 0.009%

    No Known Activations