© 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. 156181
    Prev
    Next
    INDEX
    Explanations

    website or system updates

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

    planning aspects, minimum cost, psychology

    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
    ノル
    0.54
     подроб
    0.53
     분석
    0.52
     Нор
    0.51
    読み
    0.50
     halfway
    0.49
    ˡ
    0.49
    𝟭
    0.49
    ᆺ
    0.48
     Пара
    0.47
    POSITIVE LOGITS
     gestaltet
    0.42
     உய
    0.40
     কেন্দ্রে
    0.40
     soie
    0.40
    不仅仅
    0.40
    erian
    0.39
    sina
    0.39
     energet
    0.39
     پھر
    0.39
     الحديد
    0.39
    Activations Density 0.000%

    No Known Activations