© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    consequences of time

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

    over time,

    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
     চলছে
    0.55
     आहे
    0.52
    !';
    0.50
     তখনই
    0.49
     sequential
    0.49
    ুমাত্র
    0.48
     looming
    0.48
    आधी
    0.48
     যায়নি
    0.47
     COW
    0.47
    POSITIVE LOGITS
    u
    0.56
    r
    0.54
    т
    0.51
     інших
    0.50
     éventuellement
    0.49
    ്യ
    0.48
    ת
    0.48
    Other
    0.48
     dėl
    0.48
    Ça
    0.47
    Activations Density 0.029%

    No Known Activations