© 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. 99398
    Prev
    Next
    INDEX
    Explanations

    banking and financial reserves

    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
     stanow
    -0.77
     orifice
    -0.76
    üng
    -0.76
    ุณ
    -0.75
    losure
    -0.74
    PostBack
    -0.72
     चार
    -0.72
    ujete
    -0.71
    CardModule
    -0.71
     उत्तर
    -0.71
    POSITIVE LOGITS
     deposits
    1.38
     reserve
    1.17
     deposit
    1.13
     reserves
    1.09
     depósitos
    0.99
    reserve
    0.93
     reservas
    0.93
     Reserves
    0.92
    Reserve
    0.91
     vault
    0.89
    Activations Density 0.008%

    No Known Activations