© 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. 24225
    Prev
    Next
    INDEX
    Explanations

    implement core banking

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

    Turkish Ebru art

    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
     inkább
    0.42
    ترام
    0.40
    inden
    0.39
    erp
    0.39
    %).
    0.39
    แปล
    0.39
    囩
    0.38
    பு
    0.38
     inverses
    0.38
    ണ്ഡ
    0.38
    POSITIVE LOGITS
    ,​
    0.46
    खरी
    0.40
    。<
    0.39
    ,:
    0.39
    ၊
    0.38
     Coin
    0.38
    、《
    0.38
     Festive
    0.38
    、“
    0.38
    <mask>
    0.38
    Activations Density 0.000%

    No Known Activations