© 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. 212226
    Prev
    Next
    INDEX
    Explanations

    opportunities and marine

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

    multi-lingual structure

    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
     କରି
    0.54
     電動
    0.48
     সন্তান
    0.47
     فَ
    0.47
     그러
    0.46
     tachycardia
    0.46
     පමණ
    0.46
     constitutions
    0.46
     भोजन
    0.46
     hamburgers
    0.46
    POSITIVE LOGITS
    傛
    0.51
     Derby
    0.50
     New
    0.47
     bekend
    0.47
     Thames
    0.47
     Handling
    0.46
    ro
    0.46
    ס
    0.45
    साम
    0.45
    くなる
    0.45
    Activations Density 0.000%

    No Known Activations