© 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. 109267
    Prev
    Next
    INDEX
    Explanations

    attributions of actions and creations

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

    credited with

    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
     Posteriormente
    0.46
     cps
    0.45
     and
    0.44
     igen
    0.44
     anteriores
    0.43
     externally
    0.42
     contraceptives
    0.41
     s
    0.41
     frust
    0.40
     terrest
    0.40
    POSITIVE LOGITS
     ምክ
    0.55
     навіть
    0.49
     તેમની
    0.49
    ગાહી
    0.49
    פי
    0.48
    แห่ง
    0.48
     маги
    0.48
    RMSE
    0.47
    АР
    0.47
    רי
    0.46
    Activations Density 0.001%

    No Known Activations