© 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. 170
    Prev
    Next
    INDEX
    Explanations

    DeSantis Breindel

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

    login, SCP, shall, communication

    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
     foarte
    0.32
     rất
    0.32
     nécessaires
    0.32
     ":"
    0.31
     принято
    0.31
     masterpieces
    0.30
     noastră
    0.30
     unserem
    0.29
     skall
    0.29
     ก็
    0.29
    POSITIVE LOGITS
    targeting
    0.37
    併
    0.34
    ್ಯೂ
    0.34
    ಾನ
    0.34
    formerly
    0.33
    tgts
    0.33
     таксама
    0.32
    ās
    0.32
    િલે
    0.32
    共
    0.32
    Activations Density 0.520%

    No Known Activations