© 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. 87325
    Prev
    Next
    INDEX
    Explanations

    justice, Republic, private, cells, accuracy, New

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

    GPT followed by will

    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
    يبة
    0.61
    r
    0.50
    bett
    0.46
     Offline
    0.44
    <0xE3>
    0.44
    笙
    0.44
    腩
    0.43
    شكال
    0.43
    finn
    0.43
    ../../../
    0.43
    POSITIVE LOGITS
    последствии
    0.58
    פק
    0.50
     பண்ப
    0.50
     mue
    0.48
     enunci
    0.48
    ब्ल्यू
    0.48
     consult
    0.47
     ataupun
    0.47
     precisa
    0.47
     adulto
    0.47
    Activations Density 0.000%

    No Known Activations