© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9707
    Prev
    Next
    INDEX
    Explanations

    Communication is key

    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_16k_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
    reloadData
    0.52
    ih
    0.50
     ="
    0.49
    (""
    0.49
     ((
    0.48
    ate
    0.47
    culares
    0.47
    登場
    0.47
     squares
    0.46
     <-
    0.46
    POSITIVE LOGITS
    ен
    0.48
    тения
    0.46
     päät
    0.46
     Avenue
    0.41
     Wellesley
    0.41
    ويل
    0.41
    ството
    0.40
     OJ
    0.40
     invasive
    0.40
     June
    0.39
    Activations Density 0.087%

    No Known Activations