© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11554
    Prev
    Next
    INDEX
    Explanations

    enough memory or CPU

    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
     in
    0.67
     it
    0.60
     as
    0.59
      
    0.57
     to
    0.57
     The
    0.57
     all
    0.57
     so
    0.55
    ,
    0.55
    0.55
    POSITIVE LOGITS
    ﭥ
    0.59
    chyné
    0.57
    ﮅ
    0.57
    <unused635>
    0.57
     bottlene
    0.57
     potranno
    0.57
    𒅎
    0.57
    <unused256>
    0.56
    <unused418>
    0.56
    <unused1103>
    0.56
    Activations Density 0.000%

    No Known Activations