© 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. 11835
    Prev
    Next
    INDEX
    Explanations

    on a list

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

    on phrases

    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
     behalf
    0.43
    ♠
    0.42
    ◾
    0.40
    ++){
    0.39
     samedi
    0.38
    Wed
    0.37
     سما
    0.36
    숲
    0.35
    年月日
    0.35
    myCollision
    0.35
    POSITIVE LOGITS
     لیست
    0.52
     list
    0.51
     liste
    0.49
     LIST
    0.48
     lista
    0.48
     Lista
    0.48
     lijst
    0.47
     lists
    0.47
    名单
    0.45
     सूची
    0.43
    Activations Density 0.113%

    No Known Activations