© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42225
    Prev
    Next
    INDEX
    Explanations

    multilingual text processing

    np_acts-logits-general · gemini-2.5-flash-lite

    Teltonika

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    یکم
    0.54
    在
    0.53
    ঢাকা
    0.50
    बड़े
    0.50
     दस
    0.50
    ង
    0.49
     Jawa
    0.49
     langen
    0.48
    कुछ
    0.48
     estudantes
    0.48
    POSITIVE LOGITS
    口
    0.44
     التر
    0.43
     той
    0.42
    的方向
    0.42
    ergic
    0.40
    口的
    0.40
     Porta
    0.39
     நின்று
    0.39
     extiende
    0.39
     Gli
    0.39
    Activations Density 0.000%

    No Known Activations