© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14036
    Prev
    Next
    INDEX
    Explanations

    Metal-Oxide-Semiconductor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ngo
    1.83
    ாவ
    1.82
    ting
    1.70
     présent
    1.68
    ا
    1.65
     appar
    1.65
    aceutical
    1.63
    K
    1.58
     tremendously
    1.57
     මෙම
    1.56
    POSITIVE LOGITS
    hood
    2.06
    SACTION
    1.96
    пря
    1.92
    िसोदिया
    1.91
    нцип
    1.91
    AndKeys
    1.91
     errorHandler
    1.91
    书记
    1.90
     умолчанию
    1.89
     apiKey
    1.89
    Activations Density 0.001%

    No Known Activations