© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127991
    Prev
    Next
    INDEX
    Explanations

    acronyms following based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -1.42
     their
    -1.13
     these
    -1.11
     a
    -1.09
    nhi
    -1.05
    tuy
    -1.02
     einfacher
    -1.02
     roś
    -1.01
    footnotes
    -1.00
     śnie
    -0.96
    POSITIVE LOGITS
    Два
    1.18
     extraordin
    1.15
    schuhe
    1.09
    Один
    1.06
    )
    1.05
    küche
    1.04
    خخ
    1.04
    kissen
    1.04
     cune
    1.03
     sesuatu
    1.02
    Activations Density 0.141%

    No Known Activations