© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70647
    Prev
    Next
    INDEX
    Explanations

    opposite, reverse, or still states

    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
     dil
    0.45
    çük
    0.44
    छ
    0.43
    Ö
    0.42
    தன
    0.42
    کیل
    0.41
     fecha
    0.41
    하고
    0.40
    Dil
    0.40
    clar
    0.40
    POSITIVE LOGITS
     celebrations
    0.50
    
    0.46
     celebration
    0.43
     Featuring
    0.43
    爱你
    0.42
     Celebration
    0.41
     infections
    0.41
     inspiration
    0.40
     inflammation
    0.40
    癢
    0.40
    Activations Density 0.002%

    No Known Activations