© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6196
    Prev
    Next
    INDEX
    Explanations

    near future

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

    future and predictions

    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_53_width_65k_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
    ιση
    0.43
     ሽፋን
    0.43
    𓍊
    0.41
    getFocus
    0.40
     開始
    0.35
    赧
    0.35
    alli
    0.34
    깎
    0.33
    啍
    0.33
    訌
    0.33
    POSITIVE LOGITS
     future
    5.00
    future
    4.81
     futuro
    4.47
    未来
    4.41
    Future
    4.34
    未來
    4.25
     FUTURE
    4.25
    未来的
    4.22
     Future
    4.19
    FUTURE
    4.19
    Activations Density 0.499%

    No Known Activations