© 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. 4223
    Prev
    Next
    INDEX
    Explanations

    Google TV, Bus Interface, European Union, Modular Blockchain

    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
    вающая
    0.89
    iencia
    0.88
     mocks
    0.88
    ে
    0.87
     snapshots
    0.86
    ampaikan
    0.84
    洿
    0.83
    ваны
    0.82
    ванне
    0.82
    áticos
    0.82
    POSITIVE LOGITS
    ır
    0.90
     prob
    0.88
    ication
    0.82
     iniz
    0.81
    न
    0.81
    n
    0.81
     tourne
    0.80
    lı
    0.79
     frais
    0.79
    ("");
    0.78
    Activations Density 0.000%

    No Known Activations