© 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. 173288
    Prev
    Next
    INDEX
    Explanations

    cities and international law

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

    considering the following

    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
     pierced
    0.46
    时
    0.46
    änner
    0.45
    סים
    0.45
     spike
    0.45
     descended
    0.43
    يري
    0.43
    <0x96>
    0.43
    ียด
    0.42
     a
    0.42
    POSITIVE LOGITS
     villas
    0.51
     lesqu
    0.50
    少なく
    0.48
     coagulation
    0.47
     preferentially
    0.47
     reinterpret
    0.47
     হুমকির
    0.47
     Yokohama
    0.46
     ボー
    0.46
    concurrent
    0.46
    Activations Density 0.000%

    No Known Activations