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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7274
    Prev
    Next
    INDEX
    Explanations

    connecting ideas with others

    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_16k_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
    ళ్లు
    0.41
    izzato
    0.41
    INE
    0.40
    ！
    0.38
    ‪
    0.36
    
    0.36
     bele
    0.35
    shal
    0.35
    ∶
    0.35
    ☞
    0.35
    POSITIVE LOGITS
     अन्य
    0.57
     অন্যান্য
    0.55
     একইভাবে
    0.49
     Similarly
    0.48
    其他
    0.48
     інших
    0.48
     similarly
    0.47
     سایر
    0.47
     ఇతర
    0.46
     другие
    0.46
    Activations Density 0.291%

    No Known Activations