© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240485
    Prev
    Next
    INDEX
    Explanations

    business and finance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Tower
    0.47
     接
    0.46
     আব
    0.45
     tower
    0.45
     면
    0.43
     village
    0.43
     comes
    0.42
     Best
    0.42
     mới
    0.42
     fanno
    0.42
    POSITIVE LOGITS
    ksom
    0.52
    webapp
    0.49
    Seth
    0.48
    desired
    0.47
    🗯
    0.47
    meyi
    0.46
    epub
    0.46
    penup
    0.46
    srcset
    0.45
    webhook
    0.45
    Activations Density 0.002%

    No Known Activations