© 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. 202729
    Prev
    Next
    INDEX
    Explanations

    HOA FEES and real estate

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

    bacterial genus

    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
    𝑮
    0.47
     deras
    0.42
     tecnolog
    0.42
    лим
    0.42
    чения
    0.42
     principalmente
    0.42
     deff
    0.42
     outnumbered
    0.41
    뉩
    0.41
     tolerable
    0.41
    POSITIVE LOGITS
    ugo
    0.48
    it
    0.48
    일상
    0.47
     বিশ্ব
    0.46
    iyu
    0.46
    ye
    0.46
    jx
    0.44
    vcn
    0.44
    oco
    0.44
    jn
    0.43
    Activations Density 0.000%

    No Known Activations