© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54128
    Prev
    Next
    INDEX
    Explanations

    logistic regression analysis

    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
     旗
    -1.31
    ά
    -1.21
     komende
    -1.21
     ‹
    -1.20
    所有
    -1.20
     GUIDELINES
    -1.18
    damen
    -1.18
     prega
    -1.17
     💕
    -1.16
     😄
    -1.14
    POSITIVE LOGITS
    ַּ
    1.16
    ність
    1.10
     бампер
    1.09
     octobre
    1.09
     ascer
    1.08
    uransi
    1.06
     Мы
    1.03
     of
    1.02
     atraer
    1.02
     examining
    1.01
    Activations Density 0.040%

    No Known Activations