© 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. 134729
    Prev
    Next
    INDEX
    Explanations

    Obama said or told

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

    succinctly answer

    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
    相關
    0.47
    对
    0.46
    не
    0.45
    يت
    0.44
     Related
    0.44
    أ
    0.44
    ᒐ
    0.44
    涉及
    0.43
     Blatt
    0.43
     üks
    0.43
    POSITIVE LOGITS
     camped
    0.48
     waterfall
    0.47
     chisel
    0.47
     sweatshirt
    0.47
     headband
    0.45
    breakpoint
    0.45
    myLabels
    0.45
     statically
    0.44
     beanie
    0.44
     shortened
    0.44
    Activations Density 0.000%

    No Known Activations