© 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. 15833
    Prev
    Next
    INDEX
    Explanations

    UUIDs or identifiers

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

    GUIDs and IP addresses

    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
     fadeInUp
    0.42
     COAST
    0.41
     මි
    0.40
     checkBox
    0.40
     exclusivos
    0.40
     symbolTable
    0.40
     searchText
    0.40
     루
    0.39
     peppermint
    0.39
     TabLayout
    0.39
    POSITIVE LOGITS
    례
    0.41
    StudentRecord
    0.39
    DetailsService
    0.39
    BuildConfig
    0.38
    ncies
    0.38
    うえ
    0.38
    懿
    0.37
     Zweck
    0.37
    नए
    0.37
    Issues
    0.37
    Activations Density 0.005%

    No Known Activations