© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    Tes starting words

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

    android permissions manifest

    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
    Happ
    0.40
    Ui
    0.38
    asser
    0.37
    Hist
    0.37
    𝖓
    0.37
     oportunidades
    0.37
    نج
    0.37
     निवेश
    0.37
     treści
    0.36
    Arnold
    0.36
    POSITIVE LOGITS
    permissions
    0.62
     <!--
    0.61
     Permissions
    0.60
    Uses
    0.60
    apk
    0.58
     permissions
    0.57
    uses
    0.57
     android
    0.56
     Uses
    0.55
    Permissions
    0.55
    Activations Density 0.004%

    No Known Activations