© 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. 105902
    Prev
    Next
    INDEX
    Explanations

    unmanned aerial vehicles

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

    geopolitics or national terms

    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
    __
    0.49
     ষে
    0.45
     కేసు
    0.44
     사건
    0.43
    _
    0.43
    eket
    0.43
    ils
    0.42
     සම්බන්ධ
    0.42
     representative
    0.42
    -}$
    0.41
    POSITIVE LOGITS
     ampio
    0.51
     allora
    0.45
    訾
    0.44
    ण
    0.44
     UEFI
    0.43
    Ве
    0.43
    neither
    0.43
    ATTER
    0.43
     wenig
    0.43
     almighty
    0.42
    Activations Density 0.000%

    No Known Activations