© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30131
    Prev
    Next
    INDEX
    Explanations

    for purpose or sake

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

    educational purposes

    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
    Negative Logits
     लौटने
    0.45
     Gras
    0.43
     तुम्ही
    0.43
    学家
    0.42
     Talk
    0.41
     साप
    0.41
    നിന്ന്
    0.41
    ჭ
    0.41
    உ
    0.40
     Guth
    0.40
    POSITIVE LOGITS
     purposes
    1.63
     Purposes
    1.38
     sake
    1.37
     purpose
    1.11
    purpose
    1.03
    目的
    0.98
     목적
    0.98
    的目的
    0.91
     целях
    0.90
    Purpose
    0.90
    Activations Density 0.088%

    No Known Activations