© 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-262K
    7. 7642
    Prev
    Next
    INDEX
    Explanations

    informational purposes, challenges encountered

    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
     to
    0.68
     at
    0.52
    ,
    0.51
    ya
    0.50
     spots
    0.49
     workshops
    0.48
     workspaces
    0.48
    iejs
    0.47
     Bar
    0.47
     workstations
    0.47
    POSITIVE LOGITS
     unending
    0.50
    
    0.47
    чайно
    0.46
     endless
    0.45
     miliardi
    0.44
     lawful
    0.44
     justly
    0.44
     mãn
    0.43
     vaš
    0.43
     男女
    0.43
    Activations Density 0.000%

    No Known Activations