© 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. 158727
    Prev
    Next
    INDEX
    Explanations

    webpage content

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

    freckles across

    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
    𝑵
    0.49
    ២
    0.48
    аль
    0.47
    Ⲑ
    0.46
     riserv
    0.46
    Ii
    0.46
    Ⲗ
    0.46
    lls
    0.45
    নিয়া
    0.45
    liği
    0.44
    POSITIVE LOGITS
    网页
    0.47
    纳米
    0.46
     ಬಳಸ
    0.46
     nanoparticles
    0.45
     ছোট
    0.44
     zéro
    0.43
     nanoparticle
    0.42
    港
    0.42
    published
    0.40
     কীট
    0.40
    Activations Density 0.001%

    No Known Activations