© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49497
    Prev
    Next
    INDEX
    Explanations

    financial bills and notes

    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
    conv
    -0.77
     ರ
    -0.73
     kak
    -0.71
    BREAK
    -0.67
     Loyalty
    -0.66
    lixir
    -0.65
     忠
    -0.65
     Volvo
    -0.65
     Etter
    -0.65
    track
    -0.63
    POSITIVE LOGITS
     short
    1.59
     bills
    1.44
    bills
    1.20
    短期
    1.20
     bill
    1.19
    Bills
    1.18
     Short
    1.11
    短
    1.09
     commercial
    1.09
    Short
    1.05
    Activations Density 0.017%

    No Known Activations