© 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. 7183
    Prev
    Next
    INDEX
    Explanations

    describing function or capability

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

    large language models, scale, training

    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
     gleich
    0.55
    愆
    0.54
     your
    0.52
     auteur
    0.52
     meiner
    0.52
     Philosophical
    0.51
     Historia
    0.50
     కథ
    0.50
     schön
    0.50
     Arzt
    0.50
    POSITIVE LOGITS
     अत्याधुनिक
    0.60
     lasers
    0.57
     pihaknya
    0.55
     turbines
    0.54
    <0x94>
    0.53
     বিদ্যুৎ
    0.53
     wafers
    0.53
     миллиар
    0.52
     बिजली
    0.52
     technicians
    0.51
    Activations Density 0.178%

    No Known Activations