© 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. 73521
    Prev
    Next
    INDEX
    Explanations

    sometimes, happened, selection, thousands, line

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

    depends on factors

    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
    虧
    0.46
    Funding
    0.45
    でしたが
    0.45
    ុម
    0.45
     busted
    0.45
     ক্ষতি
    0.45
    罵
    0.44
    Њ
    0.44
     pumping
    0.43
    жали
    0.43
    POSITIVE LOGITS
     sometimes
    0.50
     kadang
    0.49
     шер
    0.44
     jū
    0.44
     interesting
    0.43
     soms
    0.43
    த்துறை
    0.43
     somet
    0.42
     thoughtful
    0.42
    isst
    0.42
    Activations Density 0.002%

    No Known Activations