© 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. 157646
    Prev
    Next
    INDEX
    Explanations

    Luganda, employee, NYC

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

    collocations forming phrases

    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
     중심
    0.46
    加え
    0.44
    Clouds
    0.43
     ಎರಡು
    0.42
    лені
    0.42
     piccole
    0.42
    SaveFolder
    0.42
     애
    0.41
    Lith
    0.41
    岐阜
    0.41
    POSITIVE LOGITS
     ppl
    0.50
     NYC
    0.47
     MJ
    0.46
     abogado
    0.45
     tego
    0.44
     osoby
    0.43
     LDH
    0.42
     PLHIV
    0.42
     foreigner
    0.42
     HIV
    0.42
    Activations Density 0.006%

    No Known Activations