© 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. 8673
    Prev
    Next
    INDEX
    Explanations

    languages

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

    translate to language

    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
    <blockquote>
    0.61
    Tags
    0.44
    Berkeley
    0.39
    atti
    0.39
    <tr>
    0.38
    ovan
    0.38
    rosso
    0.38
    Labels
    0.38
    #######
    0.38
    usize
    0.38
    POSITIVE LOGITS
    Arabic
    0.93
     Arabic
    0.90
     Kyrgyz
    0.88
     Kashmiri
    0.88
     Gujarati
    0.88
     Kurdish
    0.84
     Telugu
    0.84
     Punjabi
    0.83
    Viet
    0.82
     Burmese
    0.82
    Activations Density 0.007%

    No Known Activations