© 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-262K
    7. 127912
    Prev
    Next
    INDEX
    Explanations

    Prompt tuning vs fine-tuning

    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
    Master
    0.54
    ও
    0.47
    Request
    0.45
     Harbor
    0.45
    FS
    0.45
    dot
    0.44
    UMPS
    0.44
    aap
    0.44
    site
    0.43
    1
    0.43
    POSITIVE LOGITS
     เวอร์
    0.57
     gegenüber
    0.53
    جاتا
    0.49
     وتح
    0.47
    führt
    0.46
    ോഷ്യ
    0.45
     kuin
    0.44
     منظم
    0.44
     kritis
    0.44
    جہاں
    0.44
    Activations Density 0.003%

    No Known Activations