© 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. 209145
    Prev
    Next
    INDEX
    Explanations

    cooperated with, commission these

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

    complex punctuation billing catalysts OPEN

    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
    Nw
    0.49
    Tata
    0.46
     Bess
    0.45
    ...?
    0.45
    ಜು
    0.45
    ...");
    0.45
    Cz
    0.44
    즈
    0.44
    ...(
    0.44
    B
    0.44
    POSITIVE LOGITS
    ᱘
    0.52
    φε
    0.51
    λοι
    0.49
     ocurre
    0.48
     ответственности
    0.45
    irono
    0.45
     réun
    0.45
    であった
    0.44
     weiteren
    0.43
    压
    0.43
    Activations Density 0.000%

    No Known Activations