© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2122
    Prev
    Next
    INDEX
    Explanations

    code variables and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     machined
    0.94
     computable
    0.92
     SSID
    0.88
     $[-
    0.86
     SaaS
    0.84
     SVM
    0.84
     OBD
    0.83
    ✓
    0.83
     ডিফ
    0.83
    ㅀ
    0.82
    POSITIVE LOGITS
     hor
    0.73
    こんな
    0.71
     below
    0.70
    紹介
    0.70
     island
    0.69
     pulau
    0.68
    export
    0.68
     stories
    0.67
    気軽
    0.66
     هذه
    0.66
    Activations Density 0.220%

    No Known Activations