© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1286
    Prev
    Next
    INDEX
    Explanations

    list item separators

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

    AI, programming, languages

    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
     jihad
    0.28
     convencional
    0.27
     antagonistic
    0.26
     desigual
    0.26
    :'],
    0.25
     agrad
    0.25
     amput
    0.25
     jut
    0.25
     emergent
    0.25
     úlo
    0.25
    POSITIVE LOGITS
    adda
    0.26
    অথ
    0.25
    ocos
    0.25
    ahat
    0.24
    ociazione
    0.24
    ots
    0.24
    anda
    0.23
              
    0.23
    Цент
    0.22
    
    0.22
    Activations Density 0.087%

    No Known Activations