© 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. 106293
    Prev
    Next
    INDEX
    Explanations

    Yet followed by contrasting element

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

    contrasting conjunction

    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
    ו
    0.86
    ва
    0.85
    erate
    0.84
    ة
    0.84
    िंग
    0.84
    :
    0.84
    ing
    0.83
     व
    0.83
    ίναι
    0.82
    ן
    0.82
    POSITIVE LOGITS
    c
    1.05
    b
    1.04
    k
    0.95
    p
    0.84
    ش
    0.82
    س
    0.81
     in
    0.80
    x
    0.77
    在
    0.75
    to
    0.74
    Activations Density 0.025%

    No Known Activations