© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8157
    Prev
    Next
    INDEX
    Explanations

    moon count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     Sinha
    1.10
     mesons
    0.93
     Euros
    0.84
     useRef
    0.81
     parametrization
    0.80
    ށ
    0.79
     मॉक
    0.79
    𝙢
    0.79
    renewcommand
    0.78
    mouseleave
    0.77
    POSITIVE LOGITS
    সমূহ
    1.27
    の一つ
    1.24
     suivante
    1.11
    들이
    1.07
    いくつか
    1.07
    들을
    1.07
     সমূহ
    1.06
     erster
    1.02
    들에
    1.01
    हरू
    0.99
    Activations Density 0.277%

    No Known Activations