© 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. 77537
    Prev
    Next
    INDEX
    Explanations

    order independent pairs

    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
     then
    0.39
     clashed
    0.38
     replaced
    0.36
     BS
    0.36
     $(\
    0.35
    ↵
    0.35
     BD
    0.35
     cleaning
    0.34
     Chelsea
    0.34
     leaking
    0.34
    POSITIVE LOGITS
    NSNumber
    0.46
    Itoa
    0.44
    แม้
    0.44
    листи
    0.43
    ovaž
    0.42
    遢
    0.42
    すら
    0.41
     арт
    0.41
     elenco
    0.40
    supportsFocus
    0.40
    Activations Density 0.016%

    No Known Activations