© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5182
    Prev
    Next
    INDEX
    Explanations

    variable assignments

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

    variable assignments

    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
    (("
    0.42
     partid
    0.42
    пас
    0.41
    ("\\
    0.41
     konkre
    0.41
    (""))
    0.40
    '][:
    0.39
    ഹൃ
    0.39
    েম্বর
    0.39
    ()>
    0.38
    POSITIVE LOGITS
     =
    0.71
     ={
    0.69
    Promise
    0.68
    Reducer
    0.67
    Middleware
    0.63
    Timeout
    0.61
    Promises
    0.60
    Schema
    0.57
    ={
    0.56
    axios
    0.55
    Activations Density 0.001%

    No Known Activations