© 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. 156379
    Prev
    Next
    INDEX
    Explanations

    according to

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

    according to

    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
    વાડી
    0.47
    化
    0.43
    வர
    0.43
    ප
    0.43
    ن
    0.42
    पा
    0.42
    පු
    0.41
    funcs
    0.41
    ීර
    0.41
    வலை
    0.41
    POSITIVE LOGITS
     zgodnie
    0.48
     gewährleisten
    0.48
     अकॉर्डिंग
    0.48
     rusak
    0.48
     memastikan
    0.47
    ﹕
    0.47
     volgens
    0.47
     menurut
    0.46
     gewährle
    0.46
     termini
    0.46
    Activations Density 0.001%

    No Known Activations