© 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. 68281
    Prev
    Next
    INDEX
    Explanations

    recurring fee, with four, having one

    np_acts-logits-general · gemini-2.5-flash-lite

    returning backby providingDry Heat

    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
     Salud
    0.41
     reverting
    0.38
    ¬
    0.37
    很不
    0.37
    PIO
    0.36
     reversal
    0.36
     pharmacist
    0.36
     সরিয়ে
    0.36
     Fats
    0.36
     સામાન્ય
    0.35
    POSITIVE LOGITS
    শত
    0.43
    ჲ
    0.43
    िरिक्स
    0.42
    jobNumber
    0.40
    ন্দর
    0.40
    ϙ
    0.40
    benzoimidazole
    0.39
     পিতৃ
    0.39
    を中心
    0.39
    দ্দিক
    0.39
    Activations Density 0.000%

    No Known Activations