© 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. 153726
    Prev
    Next
    INDEX
    Explanations

    financial position and categories

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

    multilingual text and code snippets

    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
    are
    0.55
    ari
    0.53
    ett
    0.45
    ert
    0.44
    );
    0.43
    and
    0.43
    avelin
    0.43
     {
    0.43
    ges
    0.43
     veteran
    0.42
    POSITIVE LOGITS
    Пла
    0.52
    佝
    0.52
    Рабо
    0.51
    Những
    0.51
    퐫
    0.51
    녠
    0.51
    ଐ
    0.50
    Thời
    0.50
    刄
    0.49
     노트북
    0.48
    Activations Density 0.000%

    No Known Activations