© 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. 12538
    Prev
    Next
    INDEX
    Explanations

    describing inherent qualities and specific entities

    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
    should
    0.51
    .
    0.47
    *.
    0.45
    Should
    0.42
    ®.
    0.41
     considérée
    0.41
    কেই
    0.41
     very
    0.40
     যদি
    0.40
    ³.
    0.40
    POSITIVE LOGITS
     allows
    0.95
     ensures
    0.93
     позволяет
    0.88
     zorgt
    0.84
     обеспечивает
    0.79
     позволяют
    0.77
     enables
    0.75
     provides
    0.74
     zapewnia
    0.74
     permette
    0.72
    Activations Density 0.118%

    No Known Activations