© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84619
    Prev
    Next
    INDEX
    Explanations

    explain text structure

    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
     treats
    0.44
     scripts
    0.43
    ര
    0.43
     সক্রিয়
    0.43
     −
    0.42
     inactive
    0.42
     rebates
    0.42
    顾问
    0.42
      
    0.41
    IN
    0.41
    POSITIVE LOGITS
    yenne
    0.67
    蹶
    0.52
    älle
    0.51
     دیتے
    0.50
    uther
    0.49
    étaient
    0.48
     questi
    0.47
     ہوتے
    0.47
    俢
    0.47
    urt
    0.47
    Activations Density 0.000%

    No Known Activations