© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3693
    Prev
    Next
    INDEX
    Explanations

    peer-to-peer lending and spot trading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৃহে
    2.36
    ाइट
    2.22
    𝘢
    2.00
    𝘺
    1.95
    の子
    1.93
    全
    1.90
    ujący
    1.90
    і
    1.89
    entesque
    1.88
    ując
    1.87
    POSITIVE LOGITS
    Ễ
    2.56
    byshev
    2.19
     intended
    2.10
    די
    2.07
    बीन
    2.05
     intento
    2.04
     attempt
    2.02
     attempted
    2.02
    ⌔
    2.00
     excite
    1.99
    Activations Density 0.008%

    No Known Activations