© 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. 81628
    Prev
    Next
    INDEX
    Explanations

    coin mining, allowed to

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

    please wait, data backs

    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
    راس
    0.44
     semplici
    0.43
     adversity
    0.43
     quanta
    0.43
     অপরের
    0.42
     baratos
    0.42
    聶
    0.42
     numeracy
    0.41
    ﮑ
    0.41
     topology
    0.41
    POSITIVE LOGITS
    to
    0.57
    findById
    0.52
     startled
    0.52
     impatiently
    0.50
    mektedir
    0.50
    iskt
    0.50
     Fuels
    0.50
     commences
    0.50
    but
    0.49
    er
    0.49
    Activations Density 0.000%

    No Known Activations