© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103804
    Prev
    Next
    INDEX
    Explanations

    tax declarations

    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_34/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
    決定
    -0.72
    cinogenicity
    -0.70
     Blackburn
    -0.66
    วาง
    -0.66
     Weiter
    -0.66
    dout
    -0.65
    ímica
    -0.65
     rant
    -0.64
    toMap
    -0.64
    Butyl
    -0.63
    POSITIVE LOGITS
     declaration
    3.59
     declared
    3.39
     declare
    3.27
     declarations
    3.13
     declaring
    3.03
     declares
    2.95
    declaration
    2.83
     Declare
    2.75
    declared
    2.70
     Declaration
    2.61
    Activations Density 0.029%

    No Known Activations