© 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-16K
    7. 13225
    Prev
    Next
    INDEX
    Explanations

    never let, believe because, life especially

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

    firstly, first, first steps

    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_16k_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
    捙
    0.46
    сти
    0.46
     habitats
    0.45
    زد
    0.45
    ición
    0.44
     retains
    0.43
     digunakan
    0.43
     جاه
    0.42
     চলছে
    0.42
    含义
    0.41
    POSITIVE LOGITS
    ᅲ
    0.46
    你看
    0.44
    /**
    0.43
     Consequently
    0.43
    GameObject
    0.42
    一方面
    0.42
     frumo
    0.42
    ////
    0.41
    Therefore
    0.41
    ։
    0.41
    Activations Density 0.001%

    No Known Activations