© 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. 34-GEMMASCOPE-RES-131K
    7. 93791
    Prev
    Next
    INDEX
    Explanations

    cash and financial transactions

    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
     dando
    -0.83
    д
    -0.81
    рок
    -0.74
     Endlich
    -0.73
    ambiar
    -0.73
     всеми
    -0.72
     dolorosa
    -0.72
     elevar
    -0.72
    the
    -0.71
     Wandering
    -0.71
    POSITIVE LOGITS
    flow
    1.37
     Cash
    1.36
    Cash
    1.20
    cash
    1.16
     prizes
    1.14
     flow
    1.13
    mere
    1.09
     cash
    1.07
    flows
    1.00
     CASH
    0.99
    Activations Density 0.005%

    No Known Activations