© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2387
    Prev
    Next
    INDEX
    Explanations

    your/their/its own

    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_17_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
    ()<
    1.01
     principalmente
    0.92
     principalement
    0.90
     sonst
    0.88
     quantitatively
    0.86
    以后
    0.85
    >[]
    0.84
     प्लीज
    0.84
     <!--<
    0.83
    Otherwise
    0.83
    POSITIVE LOGITS
     own
    3.58
     Own
    3.10
     OWN
    2.89
     eigenes
    2.79
     eigene
    2.79
     eigenen
    2.79
     собственные
    2.75
    own
    2.67
     собственной
    2.61
     eigener
    2.58
    Activations Density 0.574%

    No Known Activations