© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5897
    Prev
    Next
    INDEX
    Explanations

    overfit and reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anteriores
    0.93
    о
    0.89
     externas
    0.87
     usadas
    0.83
    ﻪ
    0.82
    е
    0.82
     familiares
    0.81
     ordinances
    0.80
     fases
    0.80
     funcionários
    0.79
    POSITIVE LOGITS
    i
    1.08
    (
    1.05
    y
    1.03
    e
    0.94
    ar
    0.88
    iveness
    0.88
    lardan
    0.86
    iunea
    0.82
    lle
    0.80
    sia
    0.79
    Activations Density 0.142%

    No Known Activations