© 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. 144169
    Prev
    Next
    INDEX
    Explanations

    oz, regime, spraying

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

    cost, bouncing, missing

    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
    ท้อง
    0.53
     webhook
    0.50
    ܤ
    0.50
    וק
    0.49
    αυ
    0.49
     testimony
    0.48
     cerebro
    0.48
     phylogeny
    0.48
     casser
    0.48
    Ꮏ
    0.47
    POSITIVE LOGITS
    }")
    0.51
    ர்ச்ச
    0.49
    ()}')
    0.46
     Brid
    0.46
     доби
    0.43
     Mohr
    0.43
     Breite
    0.42
     बेटर
    0.42
     රට
    0.42
    reu
    0.41
    Activations Density 0.001%

    No Known Activations