© 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. 43130
    Prev
    Next
    INDEX
    Explanations

    math or academic subjects

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

    describing seasons or films

    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
    l
    0.60
    ja
    0.55
    t
    0.49
    ji
    0.48
     sketched
    0.47
     ebb
    0.46
    ర్థి
    0.45
     Namespace
    0.44
    h
    0.44
    槭
    0.44
    POSITIVE LOGITS
     ตาย
    0.52
    бер
    0.51
     intensifying
    0.49
    កម្ម
    0.48
     comprenant
    0.47
     リュ
    0.47
    spreading
    0.47
    suitable
    0.47
    بك
    0.47
     കല
    0.47
    Activations Density 0.001%

    No Known Activations