© 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. 14337
    Prev
    Next
    INDEX
    Explanations

    be verbs like to be

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

    creating lists, specific actions, or improvements

    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
    "+"|".
    0.31
    ܀
    0.31
    𐰇
    0.29
     whiche
    0.29
     lokalen
    0.29
    itriangular
    0.27
    $\--
    0.27
    電流
    0.27
    舝
    0.27
     سینٹی
    0.27
    POSITIVE LOGITS
     make
    0.32
     be
    0.28
     discuss
    0.27
     convince
    0.27
     continue
    0.26
     introduce
    0.26
    0.26
     really
    0.25
     provide
    0.25
     give
    0.25
    Activations Density 0.384%

    No Known Activations