© 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. 206314
    Prev
    Next
    INDEX
    Explanations

    international actors, Japan, kids

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

    handle roads or gravel

    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
    𝘵
    0.51
    𝐭
    0.50
    дек
    0.49
    том
    0.48
    чёт
    0.47
     পৃথিবীর
    0.45
    𝘸
    0.45
    ́p
    0.45
    樸
    0.44
    naive
    0.44
    POSITIVE LOGITS
     unwelcome
    0.48
    ẽ
    0.44
     invites
    0.44
     negoci
    0.43
     besuchte
    0.43
     chicken
    0.42
     niej
    0.42
     reprendre
    0.42
     delay
    0.42
     wybrać
    0.42
    Activations Density 0.001%

    No Known Activations