© 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-262K
    7. 75669
    Prev
    Next
    INDEX
    Explanations

    against risks, restrict sexual, space and time

    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
    ху
    0.52
    기를
    0.51
     или
    0.48
    되지
    0.47
    または
    0.46
    หรือ
    0.46
     ಅಥವಾ
    0.46
    或
    0.46
    ّد
    0.45
     または
    0.45
    POSITIVE LOGITS
     hopeless
    0.47
     kar
    0.47
     leis
    0.46
     তুলনায়
    0.46
     tourism
    0.46
     অতিরিক্ত
    0.45
     famously
    0.44
     carer
    0.44
    ärk
    0.43
    ow
    0.43
    Activations Density 0.007%

    No Known Activations