© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84779
    Prev
    Next
    INDEX
    Explanations

    predicting future based on past

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $\$
    0.40
    carlo
    0.38
    hee
    0.38
    helium
    0.38
     prud
    0.38
    かもしれませんが
    0.38
    までは
    0.38
    ﻻ
    0.38
    poster
    0.37
     fillers
    0.37
    POSITIVE LOGITS
    差异
    0.44
     Strukturen
    0.43
     ADDRESS
    0.40
     và
    0.40
     Addresses
    0.40
    urdy
    0.39
     ambientes
    0.39
     Address
    0.38
     environments
    0.38
    िकास
    0.38
    Activations Density 0.002%

    No Known Activations