© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9684
    Prev
    Next
    INDEX
    Explanations

    Kirk names and places

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

    words starting with kir

    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_40_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
    simple
    0.40
    ()}\
    0.38
     simple
    0.38
    determination
    0.37
    ಾದರೆ
    0.37
    Paxos
    0.36
    ಾಗ
    0.36
    day
    0.35
    message
    0.35
     Daily
    0.35
    POSITIVE LOGITS
     KIR
    0.46
    䒑
    0.44
     kir
    0.43
    bride
    0.41
    君
    0.40
    Kir
    0.39
     предме
    0.38
     erhältlich
    0.37
    ukkan
    0.36
    ilion
    0.36
    Activations Density 0.071%

    No Known Activations