© 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. 181681
    Prev
    Next
    INDEX
    Explanations

    financing for 6 months

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

    related to pipeline or hemoglobin

    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
     الان
    0.52
    s
    0.51
     kres
    0.50
    ل
    0.47
    ਾਂ
    0.47
     lighten
    0.47
     laurels
    0.47
     entrees
    0.46
     incorporate
    0.45
    dail
    0.45
    POSITIVE LOGITS
    .).
    0.44
     ).
    0.43
    .").
    0.43
    )?
    0.43
     (°
    0.41
     ».
    0.39
    やか
    0.39
    یدی
    0.39
    .?
    0.39
    Begriffsklär
    0.39
    Activations Density 0.001%

    No Known Activations