© 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. 123426
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating completed actions

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

    past actions and events

    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
    on
    0.63
     i
    0.57
    is
    0.55
     menggambarkan
    0.54
     and
    0.54
    l
    0.53
     Gipps
    0.52
     is
    0.52
    U
    0.52
    and
    0.51
    POSITIVE LOGITS
    在了
    0.76
     recientemente
    0.70
     недавно
    0.68
     recentemente
    0.64
    떴
    0.64
     вчера
    0.62
    了他
    0.62
     dejaron
    0.61
    了一个
    0.61
     récemment
    0.61
    Activations Density 0.372%

    No Known Activations