© 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-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 52734
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios and temporal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trá
    0.61
    ité
    0.50
    を追加
    0.47
    ovanie
    0.47
     ការ
    0.47
    ただし
    0.46
     காட்டு
    0.46
    
    0.45
     činn
    0.45
     tärke
    0.44
    POSITIVE LOGITS
     Baby
    0.41
     Coffee
    0.40
     Greenhouse
    0.38
     pixels
    0.38
     Wave
    0.38
    στή
    0.37
    resx
    0.37
    玩笑
    0.37
     tracker
    0.37
     vl
    0.37
    Activations Density 0.005%

    No Known Activations