© 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. 87724
    Prev
    Next
    INDEX
    Explanations

    saving money or computation

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

    exploit attack crafting

    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
    ורה
    0.54
    рна
    0.48
    日起
    0.47
    ダイエット
    0.46
    资料
    0.46
    ’.
    0.46
     sativa
    0.46
    س
    0.46
    ר
    0.44
    Moves
    0.44
    POSITIVE LOGITS
    шен
    0.45
     Acá
    0.43
     ਨੇ
    0.43
     J
    0.42
     सैनिक
    0.40
     digitar
    0.40
     ഇല്ല
    0.40
     भोपाल
    0.39
     rằng
    0.39
    kA
    0.39
    Activations Density 0.000%

    No Known Activations