© 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. 82536
    Prev
    Next
    INDEX
    Explanations

    bank and piggybacking

    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
     lightsaber
    -0.76
    🚛
    -0.75
     recoverable
    -0.71
     gâ
    -0.70
     LSA
    -0.68
    biega
    -0.68
    Programma
    -0.67
     TTL
    -0.65
    foque
    -0.65
    CCN
    -0.63
    POSITIVE LOGITS
     bank
    4.19
    bank
    3.58
     Bank
    3.58
    Bank
    3.42
    BANK
    3.06
     BANK
    3.05
     banks
    2.91
    银行
    2.55
    銀行
    2.33
     Banks
    2.30
    Activations Density 0.030%

    No Known Activations