© 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. 79392
    Prev
    Next
    INDEX
    Explanations

    privacy, autonomy, rights

    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
     olsa
    0.51
     বদলে
    0.46
    ވ
    0.45
     খারাপ
    0.45
     मर्द
    0.45
     incentivize
    0.45
    嵃
    0.45
     Fakat
    0.44
     politič
    0.43
    ዃ
    0.43
    POSITIVE LOGITS
     Human
    0.47
    to
    0.46
    gt
    0.45
    ↵
    0.44
    do
    0.44
     Class
    0.44
    Human
    0.44
     we
    0.43
    tr
    0.43
    ter
    0.43
    Activations Density 0.006%

    No Known Activations