© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 147886
    Prev
    Next
    INDEX
    Explanations

    new and old

    np_acts-logits-general · gemini-2.5-flash-lite

    new solutions, innovation, new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fty
    0.45
     বিধি
    0.42
    \/
    0.41
     kJ
    0.41
    bf
    0.41
     সমুদ
    0.40
     usages
    0.39
    鱷
    0.39
    ptr
    0.39
     θ
    0.39
    POSITIVE LOGITS
     nowych
    0.60
     reimag
    0.59
     nieuwe
    0.59
     nuovi
    0.56
    น
    0.55
    新たな
    0.53
     새로운
    0.53
     innovative
    0.52
     yeni
    0.52
     новые
    0.52
    Activations Density 0.001%

    No Known Activations