© 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. 17899
    Prev
    Next
    INDEX
    Explanations

    given time

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

    encrypt, prevent, sign, authorize

    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
    ព័ន្ធ
    0.51
    鉑
    0.49
     ruthless
    0.48
     சாதன
    0.48
     lithium
    0.47
     Devices
    0.46
     Vape
    0.46
     positrons
    0.46
     martyrdom
    0.46
     g
    0.45
    POSITIVE LOGITS
    รี
    0.54
    Sew
    0.51
    ری
    0.51
    Coral
    0.50
    riend
    0.50
    どう
    0.49
    Skirt
    0.48
    楕
    0.48
    ନ
    0.48
    Worked
    0.47
    Activations Density 0.000%

    No Known Activations