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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12482
    Prev
    Next
    INDEX
    Explanations

    SCP identifiers

    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
    нием
    1.99
    ли
    1.95
    鋏
    1.88
    ю
    1.87
    ев
    1.82
    YES
    1.78
    ЕВ
    1.76
     отлич
    1.76
    مره
    1.75
    Surprisingly
    1.74
    POSITIVE LOGITS
     rzecz
    2.09
     revenu
    1.79
     estratégico
    1.78
     emphas
    1.73
    '></
    1.73
     kuasa
    1.71
     neighbourhood
    1.66
     emphasizing
    1.61
    othesis
    1.61
     প্রতিবেদনে
    1.61
    Activations Density 0.001%

    No Known Activations