© 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. 114221
    Prev
    Next
    INDEX
    Explanations

    Illuminate facades validator schema route

    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
    CIRCLE
    0.52
     jedną
    0.45
     सो
    0.44
     sólo
    0.42
     А
    0.42
    悻
    0.41
     onBackPressed
    0.40
     From
    0.40
     Ак
    0.39
     Highland
    0.39
    POSITIVE LOGITS
    changes
    0.57
    st
    0.56
    recycl
    0.56
    research
    0.54
    mons
    0.53
    change
    0.52
    l
    0.51
    unam
    0.49
    uname
    0.49
    decre
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.