© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35970
    Prev
    Next
    INDEX
    Explanations

    past years

    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_40_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
     Approximately
    0.90
     approximately
    0.83
    Approximately
    0.73
     approx
    0.72
    approximately
    0.72
     Approx
    0.72
     aproximadamente
    0.69
    約
    0.61
     TWO
    0.61
    大约
    0.60
    POSITIVE LOGITS
     magari
    0.63
    比如
    0.58
     freaking
    0.57
     mesela
    0.55
     مثلا
    0.54
    比如说
    0.53
     पॉलिटी
    0.51
     например
    0.50
    比如說
    0.50
     เงี้ย
    0.50
    Activations Density 0.015%

    No Known Activations