© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    classification or definition prefixes

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

    definitions following colons

    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
     gahet
    0.23
    öffent
    0.22
     ufficiale
    0.22
     després
    0.22
     selaku
    0.22
     keuangan
    0.22
    .??.??"]
    0.22
     gewann
    0.22
    GoAbroad
    0.22
    Hãy
    0.22
    POSITIVE LOGITS
     Enhanced
    0.38
     P
    0.37
     SP
    0.35
     Traditional
    0.35
     Modified
    0.34
     N
    0.34
     traditional
    0.34
     L
    0.32
     PP
    0.32
     CA
    0.32
    Activations Density 1.498%

    No Known Activations