© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123750
    Prev
    Next
    INDEX
    Explanations

    past events or future actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    龗
    -1.63
     quelconque
    -1.49
    bonjour
    -1.48
     blossoming
    -1.46
     MyClass
    -1.45
    ಿದೆ
    -1.45
     AGUA
    -1.45
    Anzahl
    -1.44
    Ainsi
    -1.44
     nombreuses
    -1.44
    POSITIVE LOGITS
     it
    2.53
     one
    2.06
     I
    1.77
     we
    1.73
     or
    1.58
     in
    1.53
     had
    1.44
    :
    1.27
    頂き
    1.27
     was
    1.27
    Activations Density 0.303%

    No Known Activations