© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7230
    Prev
    Next
    INDEX
    Explanations

    preferential, understanding, full, pressure

    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
    زة
    0.51
     ਜਾਂ
    0.49
    𝙥
    0.47
     או
    0.46
     kullanım
    0.45
    モ
    0.44
    扩展
    0.44
     χρήση
    0.44
    只
    0.44
    ξει
    0.43
    POSITIVE LOGITS
     tool
    0.47
     NH
    0.46
     dom
    0.46
     Eno
    0.46
     Cambridge
    0.44
    derived
    0.43
     ESR
    0.43
     IAAF
    0.43
     scarlet
    0.43
     didReceive
    0.43
    Activations Density 0.049%

    No Known Activations