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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39532
    Prev
    Next
    INDEX
    Explanations

    volts per, Carpter, Our Mentors, Comments on, News

    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
    ratos
    -1.30
     шоколад
    -1.23
    แฟน
    -1.16
     bigger
    -1.12
    เรา
    -1.09
     voulu
    -1.08
     такой
    -1.07
    ：……
    -1.06
    oksi
    -1.06
    もいい
    -1.06
    POSITIVE LOGITS
    ⊄
    1.24
    ってみる
    1.19
    OnPage
    1.08
    衒
    1.07
     القوات
    1.06
    выя
    1.04
    王一
    1.03
    ॄ
    1.03
     benötigen
    1.01
     раздра
    1.01
    Activations Density 0.000%

    No Known Activations