© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14633
    Prev
    Next
    INDEX
    Explanations

    public services, transportation, policies

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

    public and related concepts

    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_31_width_16k_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
    ل
    0.61
     axes
    0.53
     А
    0.52
     AN
    0.50
     empl
    0.50
    ്ലാ
    0.50
     plated
    0.50
     photons
    0.50
     an
    0.49
     复
    0.49
    POSITIVE LOGITS
     सार्वजनिक
    1.33
     public
    1.29
    Public
    1.28
     Public
    1.23
     pública
    1.23
    public
    1.20
    PUBLIC
    1.17
     publique
    1.16
     pubblica
    1.13
     PUBLIC
    1.12
    Activations Density 0.145%

    No Known Activations