© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 42
    Prev
    Next
    INDEX
    Explanations

    functionality, Ventures, housed, dataSource, Bachelor, Challenge, Network

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_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
     quando
    0.83
    луйста
    0.79
     когда
    0.77
     quand
    0.76
    -
    0.75
     vouloir
    0.75
     хочу
    0.74
    Wake
    0.73
     عندما
    0.73
     cuando
    0.73
    POSITIVE LOGITS
    inned
    0.89
    MENT
    0.83
    πος
    0.82
    ité
    0.79
    おります
    0.77
    웁
    0.77
    挹
    0.76
    ination
    0.75
    ুরের
    0.75
    ન્ટ
    0.75
    Activations Density 0.000%

    No Known Activations