© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102854
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

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

    acronyms and abbreviated organization/technical names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    荜
    -3.14
    尨
    -2.80
    垆
    -2.75
    珖
    -2.67
    鲀
    -2.50
    鋮
    -2.44
     MEETING
    -2.44
     AUTHORITIES
    -2.42
    闼
    -2.42
     lekker
    -2.41
    POSITIVE LOGITS
    ’
    2.81
    t
    2.63
    ("
    2.47
    銦
    2.44
    u
    2.44
     sometime
    2.42
     kleineren
    2.38
     that
    2.36
    P
    2.36
     leichten
    2.30
    Activations Density 0.031%

    No Known Activations