© 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-16K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    corruption

    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_16k_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
    B
    1.44
     що
    1.28
    G
    1.24
    Point
    1.14
    F
    1.13
     а
    1.11
    ],
    1.10
    R
    1.10
    <0x95>
    1.09
    Brief
    1.06
    POSITIVE LOGITS
     conlle
    1.13
    jų
    1.13
    慗
    1.09
    Appuntamento
    1.07
     wreaths
    1.06
    邋
    1.05
     undue
    1.03
     lattices
    1.02
     glistening
    1.02
     glittering
    1.01
    Activations Density 0.289%

    No Known Activations