© 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. 29-GEMMASCOPE-2-RES-16K
    7. 975
    Prev
    Next
    INDEX
    Explanations

    greetings

    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_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
    六
    0.71
    amins
    0.71
     PDEs
    0.70
     culminates
    0.70
     circles
    0.70
     triangles
    0.70
     tripartite
    0.68
    箖
    0.68
     Circles
    0.68
    erus
    0.67
    POSITIVE LOGITS
    Hello
    1.74
    Hi
    1.62
     Hello
    1.60
     hello
    1.53
     Hi
    1.46
    Dear
    1.44
    hello
    1.42
    Hallo
    1.32
     Dear
    1.28
    Hola
    1.27
    Activations Density 1.257%

    No Known Activations