© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2654
    Prev
    Next
    INDEX
    Explanations

    Lithuanian and Russian grammar

    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
    ow
    0.74
     Rath
    0.73
     oov
    0.70
     location
    0.69
    Ō
    0.68
    گیری
    0.68
    Ms
    0.68
    仕事
    0.67
     work
    0.67
     Cat
    0.66
    POSITIVE LOGITS
     į
    0.98
     эсеп
    0.96
     kaip
    0.93
     naudoj
    0.91
     jų
    0.90
     prieš
    0.88
     už
    0.88
     ойноо
    0.87
     эмне
    0.87
     pasir
    0.85
    Activations Density 0.101%

    No Known Activations