© 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. 16903
    Prev
    Next
    INDEX
    Explanations

    since followed by a past event

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

    since followed by event or 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
     sırada
    0.55
    ות
    0.52
    ன்
    0.52
    เท
    0.51
    ώνει
    0.50
    ский
    0.49
    ्याय
    0.48
    ੇ
    0.47
    ্ড
    0.47
    ית
    0.46
    POSITIVE LOGITS
     since
    1.23
     sejak
    1.15
     منذ
    1.13
    Since
    1.10
     Since
    1.07
    since
    1.02
    自从
    1.02
    Depuis
    0.96
     seit
    0.93
     sinds
    0.93
    Activations Density 0.074%

    No Known Activations