© 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. 16056
    Prev
    Next
    INDEX
    Explanations

    starts with or begins

    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
    मिटेड
    0.97
     préférable
    0.97
    해서
    0.96
    제목
    0.95
    치는
    0.95
    withstanding
    0.95
    속
    0.95
     skala
    0.95
     soal
    0.93
    ्राफी
    0.92
    POSITIVE LOGITS
     undisclosed
    1.40
     undocumented
    1.34
     exits
    1.26
    lite
    1.24
     Crete
    1.24
    ઠા
    1.23
    η
    1.22
    uckles
    1.20
     collar
    1.16
     detained
    1.15
    Activations Density 0.001%

    No Known Activations