© 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. 72478
    Prev
    Next
    INDEX
    Explanations

    travel and camping preparations

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

    airport travel logistics

    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
     savaş
    0.44
    航
    0.43
     سلمان
    0.42
     гости
    0.42
     همچ
    0.41
     régi
    0.41
     коман
    0.40
     ناح
    0.40
     مشاهده
    0.40
     verseny
    0.40
    POSITIVE LOGITS
    res
    0.45
    bl
    0.44
    clinic
    0.44
    2
    0.43
    事前
    0.43
    icia
    0.42
    葛
    0.41
    son
    0.41
    咳
    0.41
    ​
    0.41
    Activations Density 0.007%

    No Known Activations