© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14759
    Prev
    Next
    INDEX
    Explanations

    multilingual content and categories

    np_acts-logits-general · gemini-2.5-flash-lite

    conditions or hypothetical situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tarantino
    0.51
    瑋
    0.49
     cé
    0.49
     Trip
    0.49
     Cé
    0.49
     Cochran
    0.47
     repent
    0.47
     brooch
    0.46
     pipa
    0.46
     brace
    0.46
    POSITIVE LOGITS
    धिकारिक
    0.46
    ぎ
    0.45
    豊富な
    0.44
    ال
    0.44
    र्गन
    0.43
    う
    0.43
    Multimedia
    0.42
    ალი
    0.42
    畨
    0.41
    еха
    0.41
    Activations Density 0.002%

    No Known Activations