© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35547
    Prev
    Next
    INDEX
    Explanations

    end of sentence markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CV
    0.68
    z
    0.65
    ف
    0.64
    د
    0.64
    م
    0.63
    ం
    0.62
    س
    0.61
    Agg
    0.60
    ER
    0.59
    PCR
    0.58
    POSITIVE LOGITS
     in
    0.74
     ၂
    0.68
    ."),
    0.66
     but
    0.63
     endearing
    0.61
     are
    0.60
    ாவின்
    0.60
     Encyclopædia
    0.60
     indis
    0.59
     freaking
    0.59
    Activations Density 0.053%

    No Known Activations