© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73769
    Prev
    Next
    INDEX
    Explanations

    IP address and data handling

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

    still often

    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_262k_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
    हरु
    0.51
    娀
    0.44
     kuten
    0.44
     plana
    0.43
    蓮
    0.43
    ลง
    0.42
    ง
    0.42
    ในการ
    0.41
    ično
    0.41
    窠
    0.41
    POSITIVE LOGITS
    robespierre
    0.48
     convicts
    0.47
     confessions
    0.46
     βα
    0.44
    ಷ್ಯ
    0.44
     ϒ
    0.43
     христиан
    0.43
    捶
    0.43
    βολ
    0.42
     haies
    0.42
    Activations Density 0.003%

    No Known Activations