© 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. 67295
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions

    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
     this
    -1.52
    是因為
    -1.45
     However
    -1.41
    FormUrlEncoded
    -1.41
    膾
    -1.40
    没关系
    -1.37
    entado
    -1.35
     Bearbeitung
    -1.34
    感じです
    -1.32
     provide
    -1.31
    POSITIVE LOGITS
    re
    1.59
    un
    1.41
    is
    1.34
     они
    1.32
    ?”
    1.32
    should
    1.31
    wasn
    1.30
    E
    1.28
    It
    1.27
    isn
    1.27
    Activations Density 0.000%

    No Known Activations