© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55242
    Prev
    Next
    INDEX
    Explanations

    family members

    np_acts-logits-general · gemini-2.5-flash-lite

    individuals, relationships, duality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    পাকিস্তান
    0.55
    我们
    0.53
     ইসলামাবাদের
    0.52
    ྰ
    0.52
     ইসলামাবাদ
    0.51
    পাকিস্তানের
    0.50
    లుగా
    0.49
     পাকিস্তান
    0.48
     ম্যানেজার
    0.48
    粡
    0.47
    POSITIVE LOGITS
    brid
    0.48
    0.46
    bs
    0.45
    board
    0.45
     trio
    0.45
    beda
    0.45
     crook
    0.45
     individuality
    0.43
     relatives
    0.43
     corporal
    0.43
    Activations Density 0.000%

    No Known Activations