© 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-65K
    7. 50982
    Prev
    Next
    INDEX
    Explanations

    redundant or implied information

    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
     Psal
    0.43
     m
    0.39
     buku
    0.39
     Memor
    0.39
     inventors
    0.38
     M
    0.38
     中古
    0.38
     viviendas
    0.37
    鏟
    0.37
     produk
    0.37
    POSITIVE LOGITS
     chakra
    0.46
     amenaza
    0.44
     aftermath
    0.43
    ancı
    0.43
    敚
    0.43
    权力
    0.42
    -”
    0.42
    өө
    0.41
     cytometry
    0.41
     אחרי
    0.41
    Activations Density 0.009%

    No Known Activations