© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    decided to

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

    decide 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
    ৮
    0.49
     conex
    0.47
     correl
    0.46
    都知道
    0.45
     receptor
    0.43
     range
    0.43
    ४
    0.42
     predic
    0.42
     serotonin
    0.42
    ρ
    0.42
    POSITIVE LOGITS
     decided
    0.73
     opted
    0.62
     решил
    0.61
     memutuskan
    0.60
     решила
    0.59
     forgo
    0.55
     решили
    0.54
     жить
    0.52
     décide
    0.52
     Decide
    0.51
    Activations Density 0.116%

    No Known Activations