© 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. 184441
    Prev
    Next
    INDEX
    Explanations

    membership, earthquakes, measurements, prevention, Plan, financial

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

    cost, ER, pauses, Autopilot, Treat, loop

    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
    โม
    0.46
    ეგ
    0.45
    یک
    0.45
    сында
    0.45
     কারণেই
    0.44
    어도
    0.44
    cenia
    0.44
    द
    0.44
    鏤
    0.43
     متحده
    0.43
    POSITIVE LOGITS
     vii
    0.51
     viii
    0.50
     Avery
    0.49
     promot
    0.48
     libr
    0.47
     traders
    0.47
     ven
    0.46
     merchand
    0.46
     reale
    0.46
     reagent
    0.45
    Activations Density 0.000%

    No Known Activations