© 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. 244752
    Prev
    Next
    INDEX
    Explanations

    financial leftovers and compositions

    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
     પ્રાર્થના
    0.54
     juicio
    0.47
    瑁
    0.45
    denly
    0.44
    翦
    0.43
     vectorial
    0.42
     Оде
    0.42
     griega
    0.42
    ཱ
    0.42
    Contours
    0.42
    POSITIVE LOGITS
     üz
    0.48
     my
    0.46
     uur
    0.44
     Ş
    0.43
     ervan
    0.43
     عم
    0.43
     één
    0.43
    _
    0.41
     اتر
    0.41
    lok
    0.40
    Activations Density 0.001%

    No Known Activations