© 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. 190996
    Prev
    Next
    INDEX
    Explanations

    brand new products

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

    products and their viability

    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
     resiliency
    0.45
     flavors
    0.43
    錬
    0.42
     পায়
    0.41
     resum
    0.40
    酌
    0.39
     vuln
    0.39
    flavor
    0.39
     Tarantino
    0.38
     hospitality
    0.38
    POSITIVE LOGITS
     товары
    0.59
    Ⲱ
    0.51
     proizvod
    0.48
     proizv
    0.48
     izdel
    0.48
    黛
    0.47
     Когда
    0.46
     delanter
    0.46
     produtos
    0.46
     ಉತ್ಪನ್ನ
    0.46
    Activations Density 0.000%

    No Known Activations