© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3950
    Prev
    Next
    INDEX
    Explanations

    misspelled common words

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

    Texas has

    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_53_width_65k_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
    Ça
    0.72
    
    0.70
     می‌باشد
    0.61
     œufs
    0.61
     Ça
    0.59
     Perché
    0.59
    Pokémon
    0.59
     ঊর্ধ্বতন
    0.56
    <unused2197>
    0.55
    ≔
    0.55
    POSITIVE LOGITS
     recieve
    1.85
     recieved
    1.82
     seperate
    1.78
     seper
    1.76
     occured
    1.66
     accomod
    1.66
     inital
    1.64
     sucess
    1.62
     occuring
    1.58
     succesfully
    1.57
    Activations Density 0.320%

    No Known Activations