© 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. 87279
    Prev
    Next
    INDEX
    Explanations

    to create or acquire

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

    Therefore, for, God, created

    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
    ørende
    0.47
    istar
    0.41
    缥
    0.41
     apostle
    0.40
     však
    0.38
     suggestion
    0.38
     سات
    0.37
    ለው
    0.36
     causation
    0.36
    袂
    0.36
    POSITIVE LOGITS
     Tháng
    0.41
    Monthly
    0.39
     అన
    0.38
     เดือน
    0.38
     Современ
    0.38
    :`
    0.36
    Jo
    0.36
     Monthly
    0.35
     mengapa
    0.35
    Labeled
    0.35
    Activations Density 0.038%

    No Known Activations