© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 11152
    Prev
    Next
    INDEX
    Explanations

    seriously, really, like, ridiculously

    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_262k_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
     तथा
    0.84
     Также
    0.83
    ୁ
    0.81
     نیز
    0.80
     Changel
    0.77
    および
    0.77
     Ори
    0.76
    ον
    0.76
     Кстати
    0.75
     则
    0.75
    POSITIVE LOGITS
     really
    1.07
    really
    0.98
     REALLY
    0.95
     seriously
    0.81
    Really
    0.81
     benar
    0.80
    真的
    0.76
     vraiment
    0.76
    Huh
    0.75
    Seriously
    0.75
    Activations Density 0.045%

    No Known Activations