© 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. 233841
    Prev
    Next
    INDEX
    Explanations

    high landing weight, list created by, coupled with

    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
     pomoć
    0.54
     λό
    0.50
     lø
    0.48
    以为
    0.48
    试
    0.47
     kú
    0.47
     hled
    0.47
    超
    0.47
     形
    0.46
    它
    0.46
    POSITIVE LOGITS
     punctu
    0.50
     makin
    0.46
     казни
    0.43
     sharpening
    0.43
     پسر
    0.43
     distancing
    0.42
     وزیراعظم
    0.41
     diverting
    0.41
     смерти
    0.41
    がいい
    0.41
    Activations Density 0.001%

    No Known Activations