© 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. 5487
    Prev
    Next
    INDEX
    Explanations

    English language, reports, physical descriptions

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

    RAINN

    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
    "*
    0.48
    }~
    0.45
     *\
    0.45
    ()}\
    0.45
    "...
    0.45
    '*
    0.45
     ně
    0.44
    യ്ക്ക്
    0.44
    दाश्त
    0.43
    '...
    0.42
    POSITIVE LOGITS
    ✺
    0.41
    ɦ
    0.40
     Publications
    0.39
     Vinci
    0.37
     xw
    0.37
     Papers
    0.37
    ུ
    0.37
    hton
    0.36
    ʝ
    0.36
     
    0.35
    Activations Density 0.182%

    No Known Activations