© 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. 164687
    Prev
    Next
    INDEX
    Explanations

    welfare systems, supplying items, decided to

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

    knowledge, life, whenever, hidden, for

    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
     Bă
    0.51
     Modal
    0.48
     Mean
    0.46
     Pow
    0.45
     Keyes
    0.45
     Similarly
    0.44
     Mosley
    0.43
    摑
    0.43
     Keys
    0.43
     Relief
    0.42
    POSITIVE LOGITS
     fluxo
    0.55
     competición
    0.55
    ្នក
    0.51
     जातात
    0.50
     élabor
    0.50
     дети
    0.49
     financeira
    0.49
     aritmética
    0.49
     narratives
    0.48
    imerick
    0.48
    Activations Density 0.001%

    No Known Activations