© 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. 131571
    Prev
    Next
    INDEX
    Explanations

    future and past tense constructions

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

    knowledge, success, leading, passes, emotions, validates

    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
    jo
    0.55
    ew
    0.54
    to
    0.54
    o
    0.54
    ab
    0.52
    j
    0.51
    if
    0.51
    iu
    0.50
    ib
    0.50
    Do
    0.49
    POSITIVE LOGITS
     cravings
    0.54
     superson
    0.52
     monocytes
    0.52
     stabilizers
    0.50
     oligodend
    0.50
     inmig
    0.50
     palmit
    0.50
     painkillers
    0.49
     ovipares
    0.49
    childComplexity
    0.48
    Activations Density 0.001%

    No Known Activations