© 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. 73689
    Prev
    Next
    INDEX
    Explanations

    cross-

    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
     рассла
    -0.85
    作詞
    -0.83
    '].
    -0.83
    lifes
    -0.83
    uaire
    -0.82
     mußten
    -0.81
    碰撞
    -0.79
    Until
    -0.79
    jelasan
    -0.78
     until
    -0.77
    POSITIVE LOGITS
    ваш
    0.85
    обре
    0.82
    חס
    0.81
    んですよね
    0.79
     بارداری
    0.78
    ップ
    0.77
    suk
    0.77
    vieran
    0.76
     гг
    0.76
    ସ
    0.76
    Activations Density 0.006%

    No Known Activations