© 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. 53174
    Prev
    Next
    INDEX
    Explanations

    citation references

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

    "To the moon!" slang

    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
    -
    0.44
    /
    0.44
     assist
    0.43
     centres
    0.40
     conception
    0.40
    ac
    0.40
    ナー
    0.40
    ्रांत
    0.39
     centroids
    0.39
    idal
    0.38
    POSITIVE LOGITS
    វា
    0.55
    辮
    0.49
    juang
    0.46
    ampion
    0.45
     noirâtres
    0.45
     কেবল
    0.44
    Wifi
    0.44
     پیام
    0.44
    ثت
    0.44
     kvůli
    0.44
    Activations Density 0.000%

    No Known Activations