Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11883
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

    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
     (
    -2.48
     can
    -1.36
     is
    -1.35
     "
    -1.30
     You
    -1.27
    ! 
    -1.27
     می‌تواند
    -1.26
    薔薇
    -1.26
    ……。
    -1.23
    <bos>
    -1.20
    POSITIVE LOGITS
    )
    1.81
     schreef
    1.51
    锱
    1.49
    喼
    1.45
    ことが多い
    1.40
     culo
    1.40
    ありますか
    1.40
     vitara
    1.39
     rodríguez
    1.39
    ◆◇
    1.38
    Activations Density 0.480%

    No Known Activations