© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4471
    Prev
    Next
    INDEX
    Explanations

    numerical and code steps

    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_29_width_65k_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
    Thinking
    0.80
    <unused584>
    0.66
    ){//
    0.65
    <unused2156>
    0.65
    Think
    0.64
    thinking
    0.63
    <unused2161>
    0.63
     Ngh
    0.62
     활용
    0.62
     Thinking
    0.61
    POSITIVE LOGITS
     sections
    0.59
     second
    0.59
     দ্বিতীয়
    0.58
     soon
    0.56
    又
    0.55
     $\
    0.54
     step
    0.53
     segundos
    0.53
     sección
    0.53
    そして
    0.53
    Activations Density 0.219%

    No Known Activations