© 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. 191922
    Prev
    Next
    INDEX
    Explanations

    various subjects, contexts, or events

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

    actions, states, and relation

    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
     prés
    0.53
    كيد
    0.50
    上看
    0.46
     Kür
    0.45
     ລັບ
    0.45
    框架
    0.45
    泬
    0.44
    创作
    0.44
    ্লিশ
    0.44
    遗憾
    0.44
    POSITIVE LOGITS
     adipose
    0.57
     suku
    0.52
    ー
    0.52
     with
    0.52
    oxicity
    0.50
     truce
    0.50
     entrap
    0.50
     augmenting
    0.49
     subcutaneous
    0.49
     tossing
    0.49
    Activations Density 0.001%

    No Known Activations