© 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. 28395
    Prev
    Next
    INDEX
    Explanations

    scores and ratings

    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
     plasmids
    0.25
    '
    0.24
     shipwreck
    0.24
     chromat
    0.24
     impregnated
    0.24
     expropri
    0.23
     Bitmap
    0.23
     `=`,
    0.23
     liturg
    0.23
     exe
    0.22
    POSITIVE LOGITS
    acciones
    0.26
    ƌ
    0.24
    čiti
    0.23
     cuidado
    0.23
     Foto
    0.23
    ención
    0.23
    ｭ
    0.23
    accordo
    0.23
    続きを読む
    0.23
    і
    0.23
    Activations Density 0.023%

    No Known Activations