© 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. 22-GEMMASCOPE-2-RES-65K
    7. 5168
    Prev
    Next
    INDEX
    Explanations

    say hello or goodbye

    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_22_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
    ியது
    1.29
     signifies
    1.26
     thriving
    1.26
     الزمن
    1.24
    示す
    1.22
    któ
    1.17
     nearing
    1.17
     ð
    1.16
     leverages
    1.15
    ErrorClazz
    1.15
    POSITIVE LOGITS
     goodbye
    2.84
     hello
    2.10
    不定
    1.68
     Goodbye
    1.67
     sorry
    1.62
     hola
    1.47
    实话
    1.43
    gı
    1.43
    dí
    1.42
    谎
    1.37
    Activations Density 0.036%

    No Known Activations