© 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. 125747
    Prev
    Next
    INDEX
    Explanations

    customizable, links, provided

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

    establishes, systems, or processes

    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
    പി
    0.53
    劧
    0.51
    یت
    0.50
    鞋
    0.46
    氢
    0.45
    現在
    0.44
     উপদে
    0.44
    𝕦
    0.44
    শু
    0.43
    矵
    0.43
    POSITIVE LOGITS
     Sekunden
    0.51
     paramount
    0.46
     Philips
    0.46
     mehreren
    0.46
     Quartet
    0.45
     Phillips
    0.44
     spo
    0.44
     ESPN
    0.44
     ميد
    0.44
     repr
    0.43
    Activations Density 0.002%

    No Known Activations