© 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. 122637
    Prev
    Next
    INDEX
    Explanations

    past tense associations

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

    rather than just

    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
     négoci
    0.51
     troisième
    0.49
     sanciones
    0.47
     demandé
    0.46
    gé
    0.46
    á
    0.46
    이라는
    0.45
    臓
    0.45
    BL
    0.45
    жер
    0.45
    POSITIVE LOGITS
     ok
    0.50
     该
    0.47
     पूरा
    0.45
     فور
    0.45
     Uninstall
    0.45
    很大的
    0.44
     uptime
    0.44
     Specification
    0.43
     BIG
    0.43
     Instrument
    0.42
    Activations Density 0.000%

    No Known Activations