© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28530
    Prev
    Next
    INDEX
    Explanations

    salt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বাঙ্গালীদের
    0.42
     childnya
    0.42
     படைய
    0.40
     السنوات
    0.40
     ஆடி
    0.39
     زيت
    0.39
    ]+")
    0.38
     Scaffold
    0.38
     заве
    0.38
     বাঙ্গালীর
    0.37
    POSITIVE LOGITS
     salt
    0.83
     NaCl
    0.80
     brine
    0.77
    NaCl
    0.77
    salt
    0.73
    🧂
    0.71
    Salt
    0.70
     Salt
    0.68
    鹽
    0.66
     塩
    0.63
    Activations Density 0.008%

    No Known Activations