© 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. 13285
    Prev
    Next
    INDEX
    Explanations

    explicit expressions for

    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
     использова
    -1.35
     compléter
    -1.30
    
    -1.28
    を使用
    -1.23
    を使用して
    -1.22
    を選び
    -1.22
    嵓
    -1.21
    튿
    -1.21
     délais
    -1.21
    那天
    -1.21
    POSITIVE LOGITS
     for
    2.09
     from
    1.49
     with
    1.44
     without
    1.42
     in
    1.38
     can
    1.30
     when
    1.27
     does
    1.20
     how
    1.19
     what
    1.18
    Activations Density 0.084%

    No Known Activations