© 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-262K
    7. 52470
    Prev
    Next
    INDEX
    Explanations

    specialized abilities and populations

    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
    I
    0.57
    ı
    0.57
    icots
    0.55
    ic
    0.49
    ot
    0.49
     Empor
    0.48
    ip
    0.48
    O
    0.48
    uko
    0.47
    ensor
    0.47
    POSITIVE LOGITS
    獵
    0.46
     intimid
    0.46
    靈
    0.45
     delineate
    0.43
    ᅪ
    0.43
    一道
    0.43
     सौभाग्य
    0.43
     geliştir
    0.42
    ارك
    0.42
    號
    0.42
    Activations Density 0.001%

    No Known Activations