© 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. 23442
    Prev
    Next
    INDEX
    Explanations

    last followed by temporal expressions

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

    last night, updated, chance, request, 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
    ዘ
    0.42
     loafers
    0.42
    ಬ್ಬ
    0.41
     tambour
    0.41
     plunder
    0.41
     Crusaders
    0.41
     resonators
    0.41
     liters
    0.40
    㖮
    0.39
     îns
    0.39
    POSITIVE LOGITS
     Dienstag
    0.42
     Согласно
    0.39
     Прави
    0.39
    ☰
    0.38
    oxing
    0.38
     среду
    0.38
     Кан
    0.38
     paréntesis
    0.37
    andi
    0.37
     наконец
    0.37
    Activations Density 0.009%

    No Known Activations