© 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. 5729
    Prev
    Next
    INDEX
    Explanations

    as is

    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
    iliations
    0.62
    ouse
    0.59
     Among
    0.58
    ückt
    0.57
     حوصل
    0.56
    かつ
    0.56
     hábito
    0.55
    ំ
    0.55
     piloting
    0.54
    łoż
    0.54
    POSITIVE LOGITS
     그대로
    1.87
     unaltered
    1.75
     unchanged
    1.62
    そのまま
    1.61
     unmodified
    1.58
     அப்படியே
    1.44
     untouched
    1.42
     as
    1.29
     まま
    1.26
     كما
    1.23
    Activations Density 0.141%

    No Known Activations