© 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. 223188
    Prev
    Next
    INDEX
    Explanations

    Lakes and geography

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

    partitioning, transformers, expanding

    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
     т
    0.45
    Samantha
    0.44
    اري
    0.44
    と思いますが
    0.41
    арма
    0.41
     goofy
    0.39
    ስቃ
    0.39
    ท
    0.39
     invitación
    0.38
     সৈনিক
    0.38
    POSITIVE LOGITS
     lakes
    0.55
     adjoining
    0.52
     wildfire
    0.52
     wildfires
    0.51
     直接
    0.51
     overland
    0.50
     Lakes
    0.49
     Writers
    0.49
     Juárez
    0.48
     skirting
    0.48
    Activations Density 0.001%

    No Known Activations