© 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-65K
    7. 16529
    Prev
    Next
    INDEX
    Explanations

    rewrite or rephrase text

    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_65k_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
     Этот
    0.45
    ாலம்
    0.45
    하루
    0.44
    igungen
    0.43
    गरी
    0.42
    ђено
    0.42
    ऐ
    0.42
    軾
    0.42
     ihn
    0.41
     females
    0.41
    POSITIVE LOGITS
     catchment
    0.49
    อย่า
    0.46
     sawing
    0.45
    祟
    0.45
     rej
    0.45
     подъ
    0.44
     PDC
    0.44
     మహా
    0.44
     splatter
    0.44
     butyl
    0.43
    Activations Density 0.007%

    No Known Activations