© 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. 194296
    Prev
    Next
    INDEX
    Explanations

    superb words

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

    information, excessive, skills, analysis

    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
     કારણે
    0.55
     Visualize
    0.52
    ↪
    0.51
     માટે
    0.50
    >→</
    0.49
     প্রতিষ্ঠা
    0.49
     夏季
    0.49
     contempla
    0.49
     vengono
    0.48
    étiques
    0.48
    POSITIVE LOGITS
    ط
    0.49
    xpress
    0.47
    ت
    0.46
     superiority
    0.46
    را
    0.46
     hero
    0.45
    هم
    0.45
     superbly
    0.45
     superb
    0.44
    جاد
    0.44
    Activations Density 0.000%

    No Known Activations