© 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. 53647
    Prev
    Next
    INDEX
    Explanations

    operation or task

    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
     as
    0.61
    د
    0.52
    K
    0.52
     to
    0.48
    ным
    0.47
    ق
    0.46
    ف
    0.44
    ب
    0.44
    νο
    0.43
    蔓
    0.43
    POSITIVE LOGITS
     svolge
    0.48
     sportive
    0.47
    imai
    0.46
     autonome
    0.46
    segaretro
    0.46
     autonomously
    0.45
     undertook
    0.45
     anciens
    0.44
    ⁈
    0.44
     illustrate
    0.43
    Activations Density 0.001%

    No Known Activations