© 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. 34-GEMMASCOPE-RES-131K
    4. 33845
    Prev
    Next
    INDEX
    Explanations

    ideal scenarios and abstractions

    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_34/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
    皝
    -1.17
    痱
    -1.14
    行
    -1.13
     общем
    -1.11
    荜
    -1.09
     ストラップ
    -1.08
    絝
    -1.08
     ガラス
    -1.05
    肯定会
    -1.05
    ﺀ
    -1.05
    POSITIVE LOGITS
    istic
    1.86
    istically
    1.84
    ists
    1.47
    ism
    1.22
    ization
    1.19
    mente
    1.13
    .
    1.13
     for
    1.13
    ist
    1.09
     situation
    1.09
    Activations Density 0.008%

    No Known Activations