© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    contrast or qualification

    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
     we
    0.70
     you
    0.69
    ,
    0.67
     she
    0.58
     he
    0.57
    ؛
    0.54
    ;
    0.52
     everyone
    0.52
    .
    0.52
     surjective
    0.51
    POSITIVE LOGITS
     بهذه
    0.56
    تباينه
    0.56
     또한
    0.52
     λόγω
    0.49
    Weitere
    0.49
    ̈́
    0.48
     myös
    0.46
    Kemudian
    0.46
     بسبب
    0.46
     porém
    0.45
    Activations Density 0.137%

    No Known Activations