© 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. 9105
    Prev
    Next
    INDEX
    Explanations

    case skip

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

    EventBridge, essential, Spark, mention

    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
    ༩
    0.41
    Ა
    0.39
    ütfen
    0.39
    לא
    0.39
    Todas
    0.39
    MORDOR
    0.39
    GEBURTS
    0.38
     ხელისუფ
    0.38
    ૨
    0.38
    ედერ
    0.38
    POSITIVE LOGITS
    5
    0.51
    0.50
    7
    0.48
    4
    0.46
     E
    0.45
    8
    0.45
    6
    0.44
    0
    0.43
     R
    0.43
    3
    0.43
    Activations Density 0.084%

    No Known Activations