© 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. 41281
    Prev
    Next
    INDEX
    Explanations

    past habits

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

    used to + verb

    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
     blir
    0.55
    i
    0.55
     ultimi
    0.54
     handyman
    0.48
     forze
    0.48
     miei
    0.46
    doesn
    0.46
     screwdriver
    0.45
     условий
    0.45
     neuesten
    0.45
    POSITIVE LOGITS
     autrefois
    0.55
    calup
    0.54
     옛
    0.54
    ون
    0.53
     उसी
    0.53
    śmy
    0.53
     옆
    0.52
     مثل
    0.52
     훨씬
    0.51
     (=
    0.50
    Activations Density 0.015%

    No Known Activations